From bob at ph.tn.tudelft.nl Thu Feb 1 08:29:19 2007
From: bob at ph.tn.tudelft.nl (bob@ph.tn.tudelft.nl)
Date: Thu, 1 Feb 2007 14:29:19 +0100
Subject: Connectionists: Tenure track position in pattern recognition
Message-ID: <20070201132919.GA28487@edison.et.tudelft.nl>
There is a position for an assistant professor in pattern recognition
available at Delft University of Technology in the Netherlands:
http://vacatures.ewi.tudelft.nl/index.php?taal=&m_id=50&record=126
This position has a temporary employment basis of 2 years, with the
intention of appointing the candidate permanently.
Bob Duin
--
R.P.W. Duin Phone: (31) 15 2786143
Elect. Eng., Maths and Comp. Sc. Secr: (31) 15 2786052
Delft University of Technology Fax: (31) 15 2781843
P.O. Box 5031, 2600 GA Delft mailto: r.duin at ieee.org
The Netherlands http://ict.ewi.tudelft.nl/~duin
From BerndPorr at f2s.com Thu Feb 1 11:59:13 2007
From: BerndPorr at f2s.com (Bernd Porr)
Date: Thu, 01 Feb 2007 16:59:13 +0000
Subject: Connectionists: paper: self influencing synaptic plasticity
Message-ID: <45C21C61.4070202@f2s.com>
We are pleased to announce the paper (apologies if you've received this
announcement twice):
Self-influencing synaptic plasticity: Recurrent changes of synaptic
weights can lead to specific functional properties
Minija Tamosiunaite, Bernd Porr and Florentin W?rg?tter
Abstract:
Recent experimental results suggest that dendritic and back-propagating
spikes can influence synaptic plasticity in different ways (Holthoff,
2004; Holthoff et al., 2005). In this study we investigate how these
signals could interact at dendrites in space and time leading to
*changing plasticity properties at local synapse clusters*. Similar to a
previous study (Saudargiene et al., 2004) we employ a *differential
Hebbian learning rule to emulate spike-timing dependent plasticity* and
investigate how the interaction of dendritic and back-propagating
spikes, as the post-synaptic signals, could influence plasticity.
Specifically, we will show that local synaptic plasticity driven by
spatially confined dendritic spikes can lead to the *emergence of
synaptic clusters* with different properties. If one of these clusters
can drive the neuron into spiking, plasticity may change and the now
arising global influence of a back-propagating spike can lead to a
further segregation of the clusters and possibly the dying-off of some
of them leading to more functional specificity. These results suggest
that through plasticity being a spatial and temporal local process, the
computational properties of dendrites or complete neurons can be
substantially augmented.
http://www.berndporr.me.uk/self_influ/
--
Mobile: +44 (0)7840 340069
Work: +44 (0)141 330 5237
University of Glasgow
Department of Electronics & Electrical Engineering
Room 519, Rankine Building, Oakfield Avenue,
Glasgow, G12 8LT
From wduch at is.umk.pl Thu Feb 1 13:04:55 2007
From: wduch at is.umk.pl (Wlodzislaw Duch)
Date: Thu, 1 Feb 2007 19:04:55 +0100
Subject: Connectionists: IJCNN 2007: Extended deadline for paper
submissions: 12 February 2007!!
Message-ID: <005801c7462b$7bb11790$0a01a8c0@duchnote>
Extended deadline for paper submissions: 12 February 2007!!
We have received many requests from authors in the last few days
to extend the deadline for their submissions. As a consequence the
deadline for submissions is being extended to 12 February 2007,
but please submit as soon as possible to help us minimize delays
to the paper review process. Please refer to the conference web
site for details on paper submissions.
http://www.ijcnn2007.org/
This summer is the 20th anniversary of the IJCNN, and based on our
paper submissions to date, our awesome plenary speakers, special
sessions, workshops, and tutorials, we're confident that it will
meet your expectations as the premier neural network conference.
Orlando Florida is also an exciting destination for you and your
family. The Renaissance Orlando Resort hotel is close to the
Kennedy Space Center, Seaworld, Disney World, Winter Park and many
other attractions, as you can see from the hotel and local
attractions webpage!
Please submit your papers during the extended grace period, and
join your friends and the international neiural network community
in Orlando this summer !
Jennie Si, General Chair
Ron Sun, Program Chair
From doya at irp.oist.jp Fri Feb 2 02:36:55 2007
From: doya at irp.oist.jp (Kenji Doya)
Date: Fri, 2 Feb 2007 08:36:55 +0100
Subject: Connectionists: Okinawa Computational Neuroscience Course 2007:
Call for Applications
In-Reply-To: <611A8B41-E982-4F6D-9F1A-040735D50CEE@tnb.ua.ac.be>
References: <629C9560-4409-4A20-AB78-D3C17D3613E0@tnb.ua.ac.be>
<45658221.1080302@oist.jp>
<624004DA-7BD9-4E5C-B6F4-6F09C538316A@oist.jp>
<11F3046E-428E-4435-A3E7-7DDEFFFE5EB0@tnb.ua.ac.be>
<75012139-467B-48F8-A71A-9CF00F39E5E6@tnb.ua.ac.be>
<16B623B0-EDDD-48C7-A70C-5E7F86BD65DE@stonebow.otago.ac.nz>
<4AB326D8-24AB-4546-812D-D96A83C8BD42@oist.jp>
<18556722-DCFF-4A66-B644-737B08A02D51@tnb.ua.ac.be>
<7919C31A-7797-41CF-83F6-1CAF1ED525F9@oist.jp>
<2594E28D-438E-4DA0-BB70-FCB879205E21@tnb.ua.ac.be>
<98F7DA1D-51D1-49E3-A651-5C473982E54A@oist.jp>
<64C221F9-D90E-4145-9E54-627115708DB7@stonebow.otago.ac.nz>
<61DA876D-1D84-4767-8BE5-8CFE47D20D66@oist.jp>
<8B37B6CB-F461-4E36-A93E-AAE9257FFEB7@oist.jp>
<425E6789-8B7D-43D2-8EAD-E3F2D07D3C8E@oist.jp>
<611A8B41-E982-4F6D-9F1A-040735D50CEE@tnb.ua.ac.be>
Message-ID: <4CD9866A-114A-476A-AFB5-D178DB1C733B@irp.oist.jp>
Call for Applications
OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE 2007
Neurons, Networks and Behaviors
June 26 - July 13, 2007. Okinawa, Japan.
http://www.irp.oist.jp/ocnc/2007
Application Deadline: APRIL 5TH, 2007
The aim of the Okinawa Computational Neuroscience Course is to
provide opportunities for young researchers with theoretical backgrounds
to learn the latest advances in neuroscience, and for those with
experimental
backgrounds to have hands-on experience in computational modeling.
We invite graduate students and postgraduate researchers to participate
in the course, held from June 26th through July 13th at an oceanfront
seminar house of the Okinawa Institute of Science and Technology.
Those interested in attending the course should send the materials below
by e-mail or through the course web page by APRIL 5th, 2007.
In the previous three years, OCNC focused on the brain's computation
at different levels: Bayesian computation by neural populations (2004),
learning and prediction for behavior (2005), and single neurons as
computational devices (2006). This year, OCNC will be a comprehensive
three-week course covering single neurons, networks, and behaviors with
more time for student projects. We invite those who are interested in
integrating experimental and computational approaches at each level,
as well as in bridging different levels of complexity.
The sponsor will provide lodging and meals during the course and
support travel for those without funding. We hope that this course will
be a good opportunity for theoretical and experimental neuroscientists
to meet each other and to explore the attractive nature and culture of
Okinawa, the southernmost island prefecture of Japan.
Lectures:
Tutorial 1: math and computing for experimentalists
Markus Diesmann (RIKEN)
Kenji Doya (OIST)
Tutorial 2: neurobiology for theoreticians
Gordon Arbuthnott (OIST)
Jeff Wickens (OIST)
Single Neuron Computation
Tom Bartol (Salk Institute)
Dieter Jaeger (Emory University)
Klaus Stiefel (OIST)
Network Dynamics and Information Coding
Eve Marder (Brandeis University)
Erik De Schutter (U Antwerp & OIST)
Hagai Bergman (Hebrew University)
Behavior and Cognition
Mitsuo Kawato (ATR)
Kenji Doya (OIST)
Nathaniel Daw (New York University)
Read Montague (Baylor College of Medicine)
(more to be announced)
Student Projects:
a) Single neuron modeling and analysis
b) Psychophysics experiments and modeling
c) Behavioral experiments and modeling
Students will present posters on their current works early in the
course and the results of their projects at the end of the course.
Sponsors:
Okinawa Institute of Science and Technology (OIST)
Nara Institute of Science and Technology
Japanese Neural Network Society
Co-organizers:
Erik De Schutter: University of Antwerp & OIST
Kenji Doya, OIST
Jeffery Wickens, OIST
Klaus Stiefel, OIST
Advisors:
Sydney Brenner, OIST
Mitsuo Kawato, ATR Computational Neuroscience Laboratories
Terrence Sejnowski, Salk Institute
Torsten Wiezel, Rockefeller University
******* Application *******
Please send the following by e-mail (ocnc2007 at oist.jp) or the web
application page by APRIL 5TH, 2007.
1) First name, 2) Middle initial (if any), 3) Family name, 4) Degree,
5) Date of birth, 6) Gender, 7) Nationality, 8) Affiliation, 9)
Position,
10) Advisor, 11) Postal address, 12) Nearest airpot, 13) Phone,
14) Fax, 15) E-mail, 16) Web page (if any), 17) Educational background,
18) Work experience, 19) List of publications, 20) Research interests
(up to 500 words), 21) Motivations for attending the course (up to
500 words),
22) Two referees whom we can ask recommendations (names, affiliations,
e-mail addresses), 23) Need for travel support, 24) How you learned
about the course.
We will accept 30 students based primarily on their research interests
(20) and motivations (21). We will also consider the balance of members'
research disciplines, geographic origins, and genders.
The result of selection will be informed to applicants via e-mail by
April 20th.
For more information, please visit the web page:
http://www.irp.oist.jp/ocnc/2007
******* Secretariat *******
Okinawa Computational Neuroscience Course
Okinawa Institute of Science and Technology
12-22 Suzaki, Uruma
Okinawa 904-2234, Japan
Phone: +81-98-921-3933
Fax: +81-98-921-3873
Email: ocnc2007 at oist.jp
----
Kenji Doya
Initial Research Project, Okinawa Institute of Science and Technology
12-22 Suzaki, Uruma, Okinawa 904-2234, Japan
Phone:+81-98-921-3843; Fax:+81-98-921-3873
http://www.oist.jp/
From valenti at dsi.unimi.it Fri Feb 2 13:15:30 2007
From: valenti at dsi.unimi.it (Giorgio Valentini)
Date: Fri, 02 Feb 2007 19:15:30 +0100
Subject: Connectionists: CFP: SUEMA workshop
Message-ID: <45C37FC2.7020701@dsi.unimi.it>
************************** Call for Papers ************************
Workshop on Supervised and Unsupervised Ensemble Methods and
Their Applications (SUEMA), in conjunction with IbPRIA'2007
Gerona, Spain, 4-5 June, 2007.
http://ibpria2007.udg.cat http://suema07.dsi.unimi.it
****************************************************************
Ensembles of supervised learning machines and, in particular,
ensembles of classifiers have been established as one of the main
research topics in machine learning. Recently, methods for combining
unsupervised clusterings have been proposed to improve the reliability
and to assess the validity of discovered clusters. The main goal of
this workshop is to provide a forum open to researchers from pattern
recognition and related disciplines to present and discuss problems
related to unsupervised and supervised ensemble methods with a
particular focus on their applications to real-world problems, but
considering also the theoretical reasons of the practical success of
several widely used ensemble methods.
Possible topics of the workshop include (but are not limited to):
- New ensemble methods raised from new real world supervised and
unsupervised learning problems.
- Application of ensemble methods in
various branches of science and technology with a particular focus
on:
- bioinformatics,
- computer security,
- medical informatics,
- ecology,
- economics,
- meteorology and weather forecast,
- satellite image analysis.
- Fusion of multiple-source/multi-sensor data.
- Unsupervised ensemble methods for discovering structures in
unlabeled real data.
- Unsupervised ensemble approaches to assess the
reliability/validity of clusters discovered in real data.
- Combination techniques and methods to generate multiple base
learners from different features and data.
- Classifier selection strategies for ensemble.
- Heterogeneous ensembles of base learners.
- Variants of resampling-based methods (bagging, boosting).
- Ensemble methods for supervised multi-class classification and
regression.
*** Workshop Chairs **************************************************
Oleg Okun
Machine Vision Group Infotech Oulu and Department of
Electrical and Information Engineering P.O.Box 4500,
90014 University of Oulu, Oulu - FINLAND
Email address: oleg at ee.oulu.fi
Phone: +358 8553 2898 Fax: +358 8 553 2612
Giorgio Valentini
Dipartimento di Scienze dell'Informazione
Universita` degli Studi di Milano
Via Comelico 39, 20135 Milano - ITALY
Email address: valentini at dsi.unimi.it
Phone: +39 (02) 503 16225 Fax: +39 (02) 503 16373
******* Workshop Program Committee *********************************
Carlotta Domeniconi (George Mason University, USA)
Robert Duin (Delft University of Technology, the Netherlands)
Mark Embrechts (Rensselaer Polytechnic Institute, USA)
Ana Fred (Technical University of Lisbon, Portugal)
Joao Gama (University of Porto, Portugal)
Giorgio Giacinto (University of Cagliari, Italy)
Larry Hall (University of South Florida, USA)
Ludmila Kuncheva (University of Wales, UK)
Francesco Masulli (University of Genova, Italy)
Petia Radeva (Autonomous University of Barcelona, Spain)
Juan Jose` Rodriguez (University of Burgos, Spain)
Fabio Roli (University of Cagliari, Italy)
Paolo Rosso (University of Valencia, Spain)
Carlo Sansone (University of Naples, Italy)
Jose` Salvador Sanchez (University Jaume I, Spain)
Jordi Vitria`(Autonomous University of Barcelona, Spain)
Terry Windeatt (University of Surrey, UK)
******** Submission Procedure ****************************************
Prospective authors should submit the full paper written in English to
one of the workshop chairs by email (preferably as a PDF file).
Authors are encouraged to use LATEX for the preparation of their
articles together with the corresponding class file llncs.cls. This
file as well as other relevant files can be downloaded from the IbPRIA
2007 web site (http://ibpria2007.udg.cat).
Each submitted paper not exceeding 15 A4 pages will be reviewed by at
least two members of the program committee.
Submission implies that at least one of the authors has to register
and to present the paper at workshop.
CD proceedings with accepted papers will be distributed to the
registered workshop participants.
The organizers of the workshop are working for a post-proceedings
publication of the accepted papers with an international journal or
an international computer science book series.
**************** Registration ****************************************
Workshop registration fee is 200 per participant. A reduction of 30 is
applied to participants also registered to IbPRIA'2007.
*****************Important Dates *************************************
Submission of papers : March 16, 2007
Notification of acceptance : April 13, 2007
Camera ready : April 20, 2007
Early Registration : April 10, 2007
Workshop : June 4 or 5, 2007
From sharpee at phy.ucsf.edu Sun Feb 4 19:19:25 2007
From: sharpee at phy.ucsf.edu (sharpee@phy.ucsf.edu)
Date: Sun, 4 Feb 2007 16:19:25 -0800 (PST)
Subject: Connectionists: Postdoctoral Positions in Computational Neuroscience
Message-ID:
PostDoctoral Positions in Computational Neuroscience
Full-time postdoctoral positions are available at the Crick-Jacobs Center for
Theoretical Biology, within the Salk Institute for Biological Studies, San
Diego, CA. Projects will involve work at the interface between physics and
biology, on theories of neural coding and computation. Specifically, the goals
of these projects will include: (1) formulating optimal coding strategies in
neuronal populations, and (2) developing statistical and
information-theoretical methods for charaterizing invariant neural feature
selectivity (such as that of face-selective neurons or neurons in the song bird
brain selective for its own song).
Environment: The Crick-Jacobs Center at the Salk Institute and the Center for
Theoretical Biological Physics at UCSD together offer a first-class research
and training envirnoment in the theoretical physics and computational biology.
The Salk Institute offers exposure to cutting-edge experimental biological
research in genetics, neuroscience, and cellular biological networks. For more
information, please see http://keck.ucsf.edu/~sharpee and
http://www.cnl.salk.edu/.
Candidates should have a strong quantitative background in Physics,
Mathematics, Engineering, Computer Science or Computational Neuroscience.
Completion of the PhD degree in any of these fields is required before the
start date. The start date is flexible, and could be as early as April 1st,
2007. The initial appointments will be for 1 year, and are renewable. Ability
to program in C or Fortran, Mathematica/Matlab, and some knowledge of
neuroscience is a plus, but is not required.
To apply, please send a cv, brief statement of research interests, and
three letters of reference to me by email (sharpee at phy.ucsf.edu) in PDF or text
format. Review of applications will begin on March 1st, 2007, and continue
until positions are filled.
Best regards,
Tatyana Sharpee
From Eugene.Izhikevich at nsi.edu Mon Feb 5 03:44:23 2007
From: Eugene.Izhikevich at nsi.edu (Eugene M. Izhikevich)
Date: Mon, 05 Feb 2007 00:44:23 -0800
Subject: Connectionists: Gyorgy Buzsaki elected author/curator of
"Hippocampus" in Scholarpedia
Message-ID: <45C6EE67.7050600@nsi.edu>
The election of authors for the article "Hippocampus" in the
Encyclopedia of Computational Neuroscience is completed. The letter
below was sent to Gyorgy Buzsaki from Rutgers University. If Dr. Buzsaki
accepts the invitation, he will be the first elected author/curator of
Scholarpedia.
--
Dear Dr. Gyorgy Buzsaki,
As you might know, Scholarpedia, the free peer-reviewed encyclopedia,
conducted election of authors for the article "Hippocampus" with the
goal to identify the best living expert to invite to write such an
article. The nominees (in the order of nomination) were
1. Gyorgy Buzsaki
2. Bruce McNaughton
3. Lynn Nadel
4. David Redish
5. Douglas A. Nitz
6. Richard G. M. Morris
7. Menno P. Witter
As the editor-in-chief, it is my great privilege to let you know that
you were elected to write this article for Scholarpedia
(http://www.scholarpedia.org).
The election started on 3 May 2006 and ended on 5 February 2007,
engaging 103 participants. Rules of the election are described in
http://scholarpedia.org/article/Scholarpedia:Election
In summary, each participant can vote for no more than 3 candidates.
Each vote is multiplied by the participant's Scholar Index, which
reflects the expertise and usefulness of contributions of that person to
Scholarpedia. (So that experts have greater weight in the election).
Then, the weighted sum of the votes and a soft-max procedure is used to
select the future author of the article.
I am sending you a short explanation of this project and the
instructions to reserve the article in a separate letter. Please, let me
know whether you could write this article withing a reasonable period of
time.
Sincerely yours,
Eugene M. Izhikevich ? Editor-in-Chief of Scholarpedia, the free
peer-reviewed encyclopedia.
The Neurosciences Institute, Eugene.Izhikevich at nsi.edu
10640 John J. Hopkins Drive tel:(858) 626-2063
San Diego, CA, 92121, USA fax:(858) 626-2099
From dancoisne at bccn.uni-freiburg.de Tue Feb 6 06:02:15 2007
From: dancoisne at bccn.uni-freiburg.de (Florence Dancoisne)
Date: Tue, 06 Feb 2007 12:02:15 +0100
Subject: Connectionists: Announcement for the Advanced Course in
Computational Neurosience 2007 in Arcachon, France
Message-ID: <45C86037.9080107@bccn.uni-freiburg.de>
------------------------------------------------
ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (A PENS NEUROSCIENCE SCHOOL)
August 6th - 31st 2007, ARCACHON, FRANCE
DIRECTORS:
N. Brunel (Paris, France)
P. Dayan (UCL, UK)
I. Nelken (Jerusalem, Israel)
J. Rinzel (NYU, USA)
LOCAL ORGANIZER:
Gwendal Le Masson (INSERM Bordeaux, France)
The Advanced Course in Computational Neuroscience is for advance
graduate students and postdoctoral fellows who are interested in
learning the essentials of the field.
We seek students of any nationality from a variety of disciplines
including neuroscience, physics, electrical engineering, computer
science, mathematics and psychology. Students are expected to have a
keen interest and basic background in neurobiology as well as some
computer experience.
The course has two complementary parts. Mornings are devoted to lectures
given by distinguished international faculty on topics across the
breadth of experimental and computational neuroscience. During the rest
of the day, students are given practical training in the art and
practice of neural modelling, by pursuing a project of their choosing
under the close supervision of expert tutors.
The first week of the course introduces students to essential
neurobiological concepts and to the most important techniques in
modelling single cells, networks and neural systems. Students learn how
to solve their research problems using software packages such as MATLAB,
NEST, NEURON, XPP, etc. During the following three weeks the lectures
cover specific brain areas and functions. Topics range from modelling
single cells and subcellular processes through the simulation of simple
circuits, large neuronal networks and system level models of the brain.
The course ends with project presentations by the students.
A maximum of 30 students will be accepted. Although we are actively
raising money to reduce the fees as far as possible, the current tuition
for the course will be EUR 750; and there will be an additional
contribution of EUR 750 towards the costs of lodging, breakfast and
dinner. There will be a limited number of tuition fee scholarships,
lodging waivers and travel stipends available for students who need
financial help for attending the course. We specifically encourage
applications from researchers who work in the developing world. These
students will be selected according to the normal submission procedure.
Applications, including a description of the target project must be
submitted electronically (see below) and should be accompanied by the
names and email details of two referees who have agreed to furnish
references. Applications will be assessed by a committee, with selection
being based on the following criteria: the scientific quality of the
candidate (CV) and of the project, the recommendation letters, and
evidence that the course will afford substantial benefit to the candidate.
More information and application forms can be obtained from:
http://www.neuroinf.org/courses/EUCOURSE/A07/index.shtml
Please apply electronically using a web browser.
Contact address:
- mail:
Florence Dancoisne,
Bernstein Center for Computational Neuroscience Freiburg
Albert-Ludwigs-Universitaet Freiburg
Hansastrasse 9A
79104 Freiburg, Germany
- e-mail:
dancoisne at bccn.uni-freiburg.de
APPLICATION DEADLINE: April 13th, 2007
DEADLINE FOR LETTERS OF RECOMMENDATION: April 13th, 2007
Applicants will be notified of the results of the selection procedures
by the middle of May 2007.
FACULTY (most of whom have confirmed their attendance):
Faculty:
L. Abbott (Columbia, USA)
A. Aertsen (Freiburg, Germany)
E. Ahissar (Weizmann, Israel)
M. Ahissar (Jerusalem, Israel)
A. Arieli (Weizmann, Israel)
E. De Schutter (Antwerp, Belgium)
A. Destexhe (Gif, France)
Y. Fregnac (Gif, France)
P. Latham (UCL, UK)
R. Malach (Weizmann, Israel)
D. McAlpine (UCL, UK)
A. Pouget (Rochester, USA)
I. Segev (Jerusalem, Israel)
A. Thomson (UCL, UK)
E. Vaadia (Jerusalem, Israel)
C. van Vreeswijk (Paris, France)
L. Zhaoping (UCL, UK)
Tutors:
J. Best (Ohio State, USA)
H. Cuntz (UCL, UK)
A. Kumar (Brown, USA)
M. Rudolph (Gif, France)
T. Vogels (Columbia, USA)
From s.crone at lancaster.ac.uk Sat Feb 3 13:42:13 2007
From: s.crone at lancaster.ac.uk (Crone, Sven)
Date: Sat, 3 Feb 2007 18:42:13 -0000
Subject: Connectionists: IJCNN'07 Competition - Deadline Extension
Message-ID: <84C837A579BB6B41993A00F52567675901C750C2@exchange-be3.lancs.local>
**************************************
IJCNN'07 Forecasting Competition NN3
**************************************
You have 9 days left to participate in the IJCNN'07 Forecasting
Competition NN3, using any method from computational intelligence!
The competition is held at the International Conference on Neural
Networks, Orlando, USA, August 12-17, 2007.
Your opportunities: conference publication & presentation, invitation to
journal & book publications, cash prices & awards!
********************************
Objectives
********************************
Forecast 11 or 111 time series as accurately as possible, using methods
from computational intelligence and a consistent methodology. We hope to
evaluate progress in modelling neural networks for forecasting & to
disseminate knowledge on "best practices". The competition is for
academic purposes and supported by a grant from SAS & the International
Institute of Forecasters (IIF).
********************************
Methods
********************************
The prediction competition is open to all methods of computational
intelligence, incl. feed-forward and recurrent neural networks, fuzzy
predictors, decision & regression tress, support vector regression,
hybrid approaches etc. used in financial forecasting, statistical
prediction, time series analysis
********************************
Publication of Results
********************************
The paper submitted to the IJCNN'07 in Orlando, USA, will be presented
at a dedicated workshop on 17 August 2007 of the main conference. All
accepted IJCNN'07 submissions will be
- considered for a special issue of the International Journal of
Forecasting (IJF, Elsevier) on "Neural Networks for Forecasting" (ISI
SCI, DBLP, EBSCO, ScienceDirect etc. indexed).
- invited for submission of extended versions in an edited book
"Advances in Forecasting wit Neural Networks and Computational
Intelligence", Springer (ISI SCI, DBLP etc. indexed), (pending)
- guaranteed publication as full papers in the IEEE IJCNN'07 conference
proceedings (indexed by ISI SCI etc.)
********************************
IJCNN'07 Dates & deadlines
********************************
12 February 2007 Draft IJCNN'07 paper submission due
14 May 2007 Submission of final prediction values due
17 August 2007 IJCNN'07 Workshop
15 October 2007 Submissions to full publications
Please visit the NN3 website at
http://www.neural-forecasting-competition.com/ for further instructions.
GOOD LUCK!
Sven F. Crone &
Konstantinos Nikolopoulos
_____________________________________________________
Sven F. Crone
Deputy Director, Lancaster Centre for Forecasting
Lecturer (Ass. Prof.), Department of Management Science
Lancaster University Management School
Lancaster LA1 4YX
United Kingdom
Internet http://www.lums.lancs.ac.uk
eMail s.crone at lancaster.ac.uk
_______________________________________________
From oby at cs.tu-berlin.de Tue Feb 6 03:35:21 2007
From: oby at cs.tu-berlin.de (Klaus Obermayer)
Date: Tue, 6 Feb 2007 09:35:21 +0100 (MET)
Subject: Connectionists: postdoc position
Message-ID:
Postdoctoral Position
Adaptive Algorithms for the Detection and Discrimination of Spikes in
Multi-Tetrode Recordings
3 years, salary level BAT IIa, starting date: immediate
Berlin University of Technology and Bernstein Center,
Berlin, Germany
A postdoctoral position is available within a government (BMBF) funded
collaborative research project. Goal of the project is the development
of an adaptive, on-line spike sorting method for multi-tetrode arrays.
The new technology will then be applied for the study of neural
representations during working memory tasks in primate prefrontal cortex
(in collaboration with Dr. M. Munk, Max Planck Institute for Brain
Research, Frankfurt).
The successful candidate should have a strong background in signal
processing and machine learning, and should ideally already have
research experience with the analysis of multielectrode recordings and
with spike sorting applications.
Please send applications to (preferably by email):
Prof. Dr. Klaus Obermayer, Neural Information Processing Group,
FR 2-1, Franklinstrasse 28/29, 10587 Berlin, Germany,
email: oby at cs.tu-berlin.de
Applications will be considered until position is filled.
-----------------------------------------------------------------------
Prof. Dr. Klaus Obermayer phone: 49-30-314-73442
FR2-1, NI, Fakultaet IV 49-30-314-73120
Technische Universitaet Berlin fax: 49-30-314-73121
Franklinstrasse 28/29 e-mail: oby at cs.tu-berlin.de
10587 Berlin, Germany http://ni.cs.tu-berlin.de/
From litin at iont.ru Tue Feb 6 05:24:30 2007
From: litin at iont.ru (Litinskii)
Date: Tue, 6 Feb 2007 13:24:30 +0300
Subject: Connectionists: from Leonid Litinskii, CONT RAS
Message-ID: <1877766562.20070206132430@iont.ru>
Dear colleagues,
let us start from well-known conceptions. The one-level perceptron
with one output neuron is defined by n weights w_i and by a
threshold b. At first, the output neuron creates an induced local field
v=sum (w_i x_i) -b. (1)
Then an activation function f transforms the induced local field v
into an output signal y=f(v).
We take an interest in topics that are related with the induced local
field v only. This field defines completely the form of the
separating surface. The ability of a perceptron to separate the given
set of points into two classes depends on the form of the separating
surface.
For example, a hyperplane is the separating surface corresponding to
the local field (1). Hyper-planes allow us to separate linearly
separable sets of the input points only. This is well-known as well as
the learning algorithms in this case.
If we take the induced local field in the form
v=sum(x_i -w_i)^2 -b,
the separating surface is n-dimensional sphere whose center is in the
point W and whose radius is defined by the constant b. In this case
we deal with radial basic functions. The theory of these functions is
also well-known.
It is found out that when the local field is only slightly differ from the form (1),
v = cos(X,W)-b, (2)
the separating surface is an angular sector, whose orientation and the
corner angle are defined by the values of the parameters W and b.
Such separating surface allows us to solve the XOR-problem.
We find out that a minor modification of the expression (2) allows us
to vary significantly the structure of the separating surface. In all
the cases the choosing of the parameters in Eq.(2) is realized
uniformly with the aid the gradient descent method. In other words,
with the aid of one-level perceptron and in the framework of the
uniform approach, it is possible to separate a set of the input points
into two classes. The points are distributed nearly arbitrarily in
the space.
We would like to know, if anybody studied this problem previously?
It is impossible that nobody analyzed this problem. For example,
Wl. Duch in "K-Separability" (S.Kollias et al. (Eds.): ICANN 2006, Part I,
LNCS 4131, pp. 188-197, 2006) mentions the connection between the
form of the local field (2) and the solution of the XOR-problem. But
there were no further explanations.
We'll be very grateful for any references on this topic.
Leonid Litinskii,
Center of Optical-Neural Technologies Russian Academy of Sciences
--
Best regards,
Litinskii mailto:litin at iont.ru
From ftupindr at ti.uni-bielefeld.de Wed Feb 7 09:25:04 2007
From: ftupindr at ti.uni-bielefeld.de (Ralf Moeller)
Date: Wed, 07 Feb 2007 15:25:04 +0100
Subject: Connectionists: PhD student / postdoc: Visually guided behavior
(Bielefeld)
Message-ID: <45C9E140.2040801@ti.uni-bielefeld.de>
The Computer Engineering Group at the Faculty of Technology of
Bielefeld University offers a temporary position as
doctoral or postdoctoral researcher
(salary BAT IIa, for two years three months, starting April 1st, 2007)
in a DFG-funded research project
"Visually guided behavior in complex 3D environments".
In this project, we will develop models of visual motion perception
and of the corresponding sensorimotor control strategies in insects,
transfer them into technical solutions, and test these systems in a
gantry setup. The goal is not only to imitate biological behavioral
strategies in technical systems, but also to use these systems as a
testbed for the verification of biological models in complex,
three-dimensional environments. The project runs in close cooperation
with the Dept. of Neurobiology (Prof. Dr. Martin Egelhaaf).
The details of the offer can be found at:
http://www.ti.uni-bielefeld.de/html/offers/index.html
From vcu at cs.stir.ac.uk Wed Feb 7 10:37:49 2007
From: vcu at cs.stir.ac.uk (Vassilis Cutsuridis)
Date: Wed, 7 Feb 2007 15:37:49 -0000
Subject: Connectionists: CNS 07 workshop
Message-ID: <000c01c74acd$ec2f6a70$6ffd998b@cs.ad.stir.ac.uk>
************************** Call for participation ************************
Workshop on Cortical Microcircuits: Structure, Function and Theory
Toronto, Canada, 11-12 July, 2007
http://www.cnsorg.org/cns_meeting_workshops.htm
Description:
============
To understand how perception, action, learning and memory work, we need to gather data from multiple levels of complexity and from various brain states (normal and diseased). We need to identify the neuronal groups involved in these functions, identify their different types of neurons, draw detailed circuit diagrams, determine the forms of synaptic transmission and plasticity between different neurons and study the dynamics of the cortical microcircuits at the cellular and synaptic level that comprise these neuronal groups. Mathematical and computer models are then essential in exploring how these microcircuits can account for a given function.
The goal of the present workshop is to bring together experts from experimental and computational neuroscience in order to review some of the ongoing experimental and theoretical research concerning cortical microcircuits with particular emphasis on the functional roles of the various inhibitory interneurons in the pertinent information processing.
Topics:
=======
Specific topics will include (but are not limited to):
a.. Microcircuit architectures
a.. Neocortex
b.. Hippocampus
c.. Sensory and motor systems
b.. Cross-comparison of architectures from different brain areas
c.. Identified functionality of specific microcircuits
d.. Identified functionality of specific neuronal types
e.. Plasticity and learning
Format and Attendance:
=================
The workshop will consist of:
Short Presentations: A number of selected speakers will be invited to give short presentations of their work and/or ideas to be followed by extensive discussion.
Panel Discussion: Our invited speakers will be asked to engage each other on
the various issues concerning cortical microcircuits at the end of the workshop. The audience will be strongly encouraged to participate in the discussion.
Workshop will run for either one half or a whole day, depending on interest. Attendance is open to all CNS attendees, whether or not an abstract is submitted (see below).
Submission:
===========
Prospective attendees are invited to submit a short abstract (100-200 words) on the topics outlined above or other related issues. Speakers will be selected by the organisers on the basis of these abstracts. Both position and technical reports will be considered for this workshop. To promote a lively event, with plenty of discussion, the organizers are very interested in papers taking strong positions on the issues listed above.
Submissions should be made electronically in plain text, PDF or Postscript format and should be sent (no later than May 1st) by email to Vassilis Cutsuridis or Bruce Graham:
vcu at cs.stir.ac.uk or b.graham at cs.stir.ac.uk
Organizers:
===========
Vassilis Cutsuridis
Department of Computing Science and Mathematics
University of Stirling
Stirling FK9 4LA
U.K.
Email: vcu at cs.stir.ac.uk
Bruce P. Graham
Department of Computing Science and Mathematics
University of Stirling
Stirling FK9 4LA
U.K.
Email: b.graham at cs.stir.ac.uk
Workshop Website:
=================
http://www.cnsorg.org/cns_meeting_workshops.htm
--
The University of Stirling is a university established in Scotland by
charter at Stirling, FK9 4LA. Privileged/Confidential Information may
be contained in this message. If you are not the addressee indicated
in this message (or responsible for delivery of the message to such
person), you may not disclose, copy or deliver this message to anyone
and any action taken or omitted to be taken in reliance on it, is
prohibited and may be unlawful. In such case, you should destroy this
message and kindly notify the sender by reply email. Please advise
immediately if you or your employer do not consent to Internet email
for messages of this kind.
From becker at mcmaster.ca Wed Feb 7 15:23:03 2007
From: becker at mcmaster.ca (S. Becker)
Date: Wed, 7 Feb 2007 15:23:03 -0500 (EST)
Subject: Connectionists: CVR Conference 2007: Cortical Mechanisms of Vision
Message-ID:
Dear Colleagues,
This constitutes the first announcement
and call for posters for the York University
Centre for Vision Research Conference to be held
June 19-23, 2007. A list of speakers and titles
appears below. To view abstracts and access
registration and poster submission forms, please
visit our web site:
On behalf of the CVR, I hope you will be able to attend and participate.
Sue Becker, Professor
Department of Psychology, Neuroscience & Behaviour, McMaster University
Adjunct Member, Centre for Vision Research, York University
*****
CVR Conference 2007: Cortical Mechanisms of Vision
Schedule
Organizers: Hugh R. Wilson & Doug Crawford
Tuesday, June 19
Evening reception and registration
Wednesday, June 20
Morning: Cortical Mechanisms of Object Recognition (Wilkinson)
Kari Hoffman (York): The ontology of "objects in the temporal lobe"
Bruno Rossion (Université Catholique de
Louvain): Clarifying the functional neuro-
anatomy of face processing by
combining lesion studies and neuroimaging
Kalanit Grill-Spector (Stanford):
Fine-scale functional organization of the human
ventral stream
Galia Avedan (Ben Gurion University,
Israel): An integrative approach towards
understanding the
psychological and neural basis of congenital
prosopagnosia
Afternoon: Cortical Mechanisms of Visual Attention (Tsotsos)
Max Hopf (Magdeburg, Germany):
Neuromagnetic investigations of feature and space
based attentional
selection in visual search
John Maunsell (Baylor): Attention and the
Gain of Neuronal Responses in Monkey
Visual Cortex
Leonardo Chelazzi (Verona): One or
multiple forms of feature-based attention?
Maurizio Corbetta (Washington University,
St. Louis): Functional significance of
attentional control signals
Poster Sessions
Evening Free
Thursday, June 21
Morning: Cortical Mechanisms of Motion Processing (Wilson)
J. Anthony Movshon (NYU): How cortical cells analyze visual motion
David Bradley (U of Chicago): Pattern
Velocity Computation in the Primate Visual
System
Charles Duffy (U of Rochester): Cortical Neuronal Mechanisms of Spatial
Orientation and Self-Movement Perception
Greg DeAngelis (Washington University,
St. Louis): Neural mechanisms of heading
perception: integration of visual
and vestibular signals
Afternoon: Transformations for Visually Guided Reach (Sergio)
Lauren Sergio (York): When what you see
isn't where you get: Cortical mechanisms of
vision for complex action
Alexandra Battaglia-Mayer (La Sapienza,
Rome): Motor functions of the parietal lobe
Bijan Pessaran (NYU): A relative position
code in dorsal premotor cortex
Steve Wise (NIH): Primate prefrontal
cortex and visual knowledge: Vision for
perception, action, attention, memory,
strategies, and previous or future goals
Poster Sessions
Evening Free
Friday, June 22
Morning: Cortical Mechanisms for Eye Movements (Crawford)
Jeff Schall (Vanderbilt): On the
contributions of the frontal eye field,
supplementary eye field and
anterior cingulate cortex to the guidance and
control of saccades
Steve Lisberger (UCSF): Precise encoding of smooth eye movement
in macaque frontal pursuit area
Martin Pare (Queens U): Contributions of
parietal cortex area LIP to visual behavior
Dora Angelaki (Washington University, St.
Louis): Optic flow, vestibular and eye
position signals in visual area MSTd
Afternoon: Top-down Influences of Fronto-Parietal Cortex on Vision (Fallah)
Maz Fallah (York): Oculomotor Control of Spatial Attention
James Bisley (UCLA): Top-down suppression
of a distracting popout stimulus
Joe DeSouza (York): Neural correlates of
response suppression in prefrontal cortex
Lab tours
Conference Banquet
Saturday, June 23
Morning: Visual Integration and Consciousness (Wilson & Crawford)
Frank Tong (Vanderbilt): Deciphering the
contents of perception from activity in the
human visual cortex
Mel Goodale (U of Western Ontario): A low
road to consciousness, a high road to action
Afternoon Free
Evening: Conference Barbeque & Party
--
From retienne at jhu.edu Wed Feb 7 16:20:57 2007
From: retienne at jhu.edu (Ralph Etienne-Cummings)
Date: Wed, 07 Feb 2007 16:20:57 -0500
Subject: Connectionists: Telluride Neuromorphic Workshop 2007 Announcement
Message-ID: <45CA42B9.7090100@jhu.edu>
========================================================================
Neuromorphic Engineering Workshop
Call for Applications
Sunday, JULY 1st - Saturday, JULY 21st, 2007
TELLURIDE, COLORADO
Avis COHEN (University of Maryland)
Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland)
Ralph ETIENNE-CUMMINGS (Johns Hopkins University)
Paul HASLER (Georgia Institute of Technology)
Timmer HORIUCHI (University of Maryland)
Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich,
Switzerland)
Christof KOCH (California Institute of Technology)- Past Organization
Board Member
Terrence SEJNOWSKI (Salk Institute and UCSD)
Shihab SHAMMA (University of Maryland)
Andre van SCHAIK(University of Sydney)
We invite applications for a three week summer workshop that will be
held in Telluride, Colorado from Sunday, July 1st to Saturday, July
21st, 2007. The application deadline is Friday, March 23rd, and
application instructions are described at the bottom of this document.
The 2007 Workshop and Summer School on Neuromorphic Engineering is
sponsored by the National Science Foundation, Institute of Neuromorphic
Engineering, Airforce Research Office, Eglin Airforce Research Lab,
Institute for NeuroInfomatics - ETHZ, Geogia Institute of Technology,
University of Maryland - College Park, Johns Hopkins University, and The
Salk Institute.
Last year's workshop was an exciting event and a great success. We
strongly encourage interested parties to browse through the previous
workshop web pages at: http://ine-web.org/workshops/past-workshops
GOALS:
Carver Mead introduced the term "Neuromorphic Engineering" for a new
field based on the design and fabrication of artificial neural systems,
such as vision systems, head-eye systems, and roving robots, whose
architecture and design principles are based on those of biological
nervous systems. The goal of this workshop is to bring together young
investigators and more established researchers from academia with their
counterparts in industry and national laboratories, working on both
neurobiological as well as engineering aspects of sensory systems and
sensory-motor integration. The focus of the workshop will be on active
participation, with demonstration systems and hands on experience for
all participants. Neuromorphic engineering has a wide range of
applications from nonlinear adaptive control of complex systems to the
design of smart sensors. Many of the fundamental principles in this
field, such as the use of learning methods and the design of parallel
hardware (with an emphasis on analog and asynchronous digital VLSI), are
inspired by biological systems. However, existing applications are
modest and the challenge of scaling up from small artificial neural
networks and designing completely autonomous systems at the levels
achieved by biological systems lies ahead. The assumption underlying
this three week workshop is that the next generation of neuromorphic
systems would benefit from closer attention to the principles found
through experimental and theoretical studies of real biological nervous
systems as whole systems.
FORMAT:
The three week summer workshop will include background lectures on
systems neuroscience (in particular learning, oculo-motor and other
motor systems and attention), practical tutorials on analog VLSI design,
small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects,
and special interest groups. Participants are required to take part and
possibly complete at least one of the projects proposed. They are
furthermore encouraged to become involved in as many of the other
activities proposed as interest and time allow. There will be two
lectures in the morning that cover issues that are important to the
community in general. Because of the diverse range of backgrounds among
the participants, the majority of these lectures will be tutorials,
rather than detailed reports of current research. These lectures will be
given by invited speakers. Participants will be free to explore and play
with whatever they choose in the afternoon. Projects and interest groups
meet in the late afternoons, and after dinner. In the early afternoon
there will be tutorial on a wide spectrum of topics, including analog
VLSI, mobile robotics, auditory systems, central-pattern-generators,
selective attention mechanisms, etc.
Projects that are carried out during the workshop will be centered in a
number of working groups, including:
* active vision
* audition
* motor control
* central pattern generator and locomotion
* robotics
* multichip communication
* analog VLSI
* learning
* neuroprosthetic systems
The active perception project group will emphasize vision and human
sensory-motor coordination. Issues to be covered will include spatial
localization and constancy, attention, motor planning, eye movements,
and the use of visual motion information for motor control.
The central pattern generator group will focus on small walking and
undulating robots. It will look at characteristics and sources of parts
for building robots, play with working examples of legged and segmented
robots, and discuss CPG's and theories of nonlinear oscillators for
locomotion. It will also explore the use of simple analog VLSI sensors
for autonomous robots.
The robotics group will use rovers and working digital vision boards as
well as other possible sensors to investigate issues of sensorimotor
integration, navigation and learning.
The audition group aims to develop biologically plausible algorithms and
aVLSI implementations of specific auditory tasks such as source
localization and tracking, and sound pattern recognition. Projects will
be integrated with visual and motor tasks in the context of a robot
platform.
The multichip communication project group will use existing interchip
communication interfaces to program small networks of artificial neurons
to exhibit particular behaviors such as amplification, oscillation, and
associative memory. Issues in multichip communicationwill be discussed.
LOCATION AND ARRANGEMENTS:
The summer school will take place in the small town of Telluride, 9000
feet high in Southwest Colorado, about 6 hours drive away from Denver
(350miles). Great Lakes Aviation and America West Express airlines
provide daily flights directly into Telluride. All facilities within the
beautifully renovated public school building are fully accessible to
participants with disabilities. Participants will be housed in ski
condominiums, within walking distance of the school. Participants are
expected to share condominiums.
The workshop is intended to be very informal and hands-on. Participants
are not required to have had previous experience in analog VLSI circuit
design, computational or machine vision, systems level neurophysiology
or modeling the brain at the systems level. However, we strongly
encourage active researchers with relevant backgrounds from academia,
industry and national laboratories to apply, in particular if they are
prepared to work on specific projects, talk about their own work or
bring demonstrations to Telluride (e.g. robots, chips, software).
Internet access will be provided. Technical staff present throughout the
workshops will assist with software and hardware issues. We will have a
network of PCs running LINUX and Microsoft Windows for the workshop
projects. We also plan to provide wireless internet access and encourage
participants to bring along their personal laptop.
No cars are required. Given the small size of the town, we recommend
that you do not rent a car. Bring hiking boots, warm clothes, rain gear,
and a backpack, since Telluride is surrounded by beautiful mountains.
Unless otherwise arranged with one of the organizers, we expect
participants to stay for the entire duration of this three week workshop.
FINANCIAL ARRANGEMENT:
Notification of acceptances will be mailed out around mid April 2007.
Participants are expected to pay a $800.00 workshop fee at that time in
order to reserve a place in the workshop. The cost of a shared
condominium will be covered for all academic participants but upgrades
to a private room will cost extra. Participants from National
Laboratories and Industry are expected to pay for these condominiums.
Travel reimbursement of up to $500 for US domestic travel and up to $800
for overseas travel will be possible if financial help is needed (please
specify on the application).
HOW TO APPLY:
Applicants should be at the level of graduate students or above
(i.e.postdoctoral fellows, faculty, research and engineering staff and
the equivalent positions in industry and national laboratories). We
actively encourage women and minority candidates to apply.
The application website is (after February 12th, 2007):
http://ine-web.org/telluride-conference-2007/apply/
Application will include:
* First name, Last name, Affiliation, valid e-mail address.
* Curriculum Vitae.
* One page summary of background and interests relevant to the workshop.
* Two letters of recommendation (to be sent by references directly to
"Ralph Etienne-Cummings" ).
The application deadline is Friday, March 23, 2007.
Applicants will be notified by e-mail by the end of April.
From malchiodi at dsi.unimi.it Wed Feb 7 05:42:37 2007
From: malchiodi at dsi.unimi.it (Dario Malchiodi)
Date: Wed, 7 Feb 2007 11:42:37 +0100
Subject: Connectionists: 2nd CFP: Learning from uncertain data
References: <7EB73180-8E61-4D8E-A48A-9BF001230BE9@dsi.unimi.it>
Message-ID: <891B9F9D-DFFA-41EF-8762-C999BD36DC5D@dsi.unimi.it>
Apologies for cross-posting.
Please note the modified submission procedure and the
opportunity of publishing a post-proceedings edited volume.
------------------------------------
2nd CFP: Invited session on
Learning from uncertain data
KES2007: 11th International Conference on Knowledge-Based and
Intelligent Information & Engineering Systems
in conjunction with
WIRN07: 17th Italian Workshop on Neural Networks
September 12-14, 2007 - Vietri sul Mare (SA), Italy
http://homes.dsi.unimi.it/~malchiod/WIRN07/
------------------------------------
The session will focus on research activities in the field of
learning from data when a quantitative measure of the uncertainty
affecting each data item is available, as a counterpart of the usual
samples in input to learning algorithms, gathering data to be
considered homogeneously.
------------------------------------
Topics
The session will welcome (although not limiting to) contributions on
theoretical analysis of the problem, design of machine learning
algorithms, as well as real-world applications. A non exhaustive list
of topics to focus on is the following:
* Learning algorithms
* Integration between learning and fuzzy sets
* Soft computing methods for classification and model selection
* Support vector machines and kernel methods
* Integration between optimization and learning
* Statistical methods for dealing with uncertainty
* Real-world applications of uncertainty-based learning algorithms
------------------------------------
Paper submissions
Participants are encouraged to submit papers (up to eight pages in
length) in the Springer LNCS/LNAI format. The conference proceedings
will be published by Springer-Verlag in the LNAI series. The accepted
papers for this session will also be considered for publication in a
post-proceedings edited volume.
All submissions should be uploaded through the web page
http://www.kes2007is.prosemanager.com/submitpaper.asp
specifying "IS20: Learning form uncertain data" as session name.
------------------------------------
Important dates
Paper deadline: February 28th, 2007
Notification of acceptance: April 1st, 2007
Camera-ready papers: April 30th, 2007
------------------------------------
Session chair
Dario Malchiodi
Dipartimento di Scienze dell'Informazione
Universit? degli Studi di Milano
Via Comelico 39/41 20135 Milano ITALY
T: +39 02 503 16338
F: +39 02 503 16276
E: malchiodi(AT)dsi.unimi.it
W: http://homes.dsi.unimi.it/~malchiod
------------------------------------
Conference venue
The conference will be organized in the beautiful town of Vietri sul
Mare, near Salerno. Please refer to the official KES2007 web site for
details on the conference and for travel informations.
From C.Campbell at bristol.ac.uk Wed Feb 7 10:14:47 2007
From: C.Campbell at bristol.ac.uk (ICG Campbell, Engineering Mathematics)
Date: Wed, 07 Feb 2007 15:14:47 -0000
Subject: Connectionists: Lectureship/Readership available: Bristol
University, UK
Message-ID: <13855583.1170861287@ems-iggs.enm.bris.ac.uk>
Lecturership or Readership available in the:
Department of Engineering Mathematics
University of Bristol
United Kingdom
Based in the Department of Engineering Mathematics, two permanent posts are
available
following recent research successes including a ?1.6M EPSRC grant, a Royal
Society Wolfson award,
a new doctoral training centre in Complexity Sciences and the Bristol/Bath
EngD in Systems Engineering.
Appointments will be made at either Lecturer (Grade B) or Reader level.
You will join a vibrant and unique Department that is internationally
renowned for its research
in Applied Nonlinear Mathematics and in Artificial Intelligence, Machine
Learning and Statistical
Learning Theory, with an emerging research group at the Life Sciences
Interface.
Opportunities exist to engage in collaborative research across a wide
spectrum of mathematical,
engineering, computational and biomedical topics.
You should have an established track record in any area related to the
Department's current or
emerging interests and a desire to engage in interdisciplinary teaching and
research within a dynamic
and growing Faculty of Engineering.
Grade : Lecturer Grade B - Senior Lecturer
Salary : ?30,013 - ?46,295
Vacancy ref: 12972
Contact:
Ms E.K. Weeks
Department of Engineering Mathematics,
Queen's Building,
University of Bristol, BS8 1TR
United Kingdom
E-mail: e.weeks at bristol.ac.uk
Tel: 0117 928 9734
Alternative Contact:
Prof A Champneys
E-mail: a.r.champneys at bris.ac.uk
Tel: 0117 928 7510
***Closing Date : 15 March 2007***
***Interview Date : 30 April 2007***
Contract : Permanent
Further details and an application form can be found at
https://www.bris.ac.uk/boris/jobs/ads?ID=61474
Alternatively you can telephone (0117) 954 6947, minicom (0117) 928 8894 or
E-Mail Recruitment at bris.ac.uk (stating postal address ONLY), quoting
reference number 12972.
The departmental website is at: www.enm.bris.ac.uk
The university website is at: www.bris.ac.uk
The closing date for applications is
***9.00am, 15 March 2007***
The University of Bristol is an Equal Opportunities Employer.
From emmanuel.vincent at irisa.fr Wed Feb 7 09:24:56 2007
From: emmanuel.vincent at irisa.fr (Emmanuel Vincent)
Date: Wed, 07 Feb 2007 15:24:56 +0100
Subject: Connectionists: Postdoc position at IRISA, Rennes, France
Message-ID: <45C9E138.3030600@irisa.fr>
Dear list,
We are seeking to recruit a postdoctoral researcher on the statistical
modeling of multichannel audio, applied to speaker segmentation and
separation (full subject below). The successful candidate will work
under the supervision of Drs. Guillaume Gravier and Emmanuel Vincent, in
the METISS group at IRISA, which possesses a newly-equipped room
dedicated to the exploration of future meeting environments.
Prospective candidates should have a background in multichannel signal
processing or in speech processing and hold a PhD for less than one year
or being about to obtain one. Informal enquiries may be made to Emmanuel
Vincent (emmanuel.vincent at irisa.fr) or Guillaume Gravier
(guillaume.gravier at irisa.fr).
This appointment is for 2 years, starting summer or fall 2007. Salary
will be at 28000 euros per annum. Applications must be submitted online
before march 31st at
http://www.inria.fr/travailler/opportunites/postdoc/postdoc.en.html
Joint statistical modeling of spectral, temporal and spatial audio
features, applied to speaker segmentation and separation
Most audio signals represent complex sound scenes consisting of several
overlapping sources (speakers, natural sounds, musical instruments).
These sources are usually located at different spatial positions and
exhibit different spectro-temporal characteristics. The processing of
such documents involves several challenging tasks, such as the
separation, the segmentation and more generally the description of each
source.
Existing description algorithms are mostly designed for one-microphone
recordings and rely on statistical modeling of spectral features. Yet,
in many application environments, multiple microphones are available
thus providing valuable spatial information. Beamforming algorithms are
then typically employed to determine at each instant the number of
sources and their locations based on spatial features. These algorithms
can improve the detection of overlapping sources. However their
robustness decreases for small microphone arrays or with moving sources.
The goal of this project is to define a unified statistical modeling
framework for the joint exploitation of spectral, temporal and spatial
information in multichannel audio signals. Dynamic state-based models
offer a promising approach for the description of some extracted
spectral and spatial features as a function of some hidden states
associated with different sources and positions. A first stage of the
project could consist of extending the state-of-the-art one-microphone
segmentation model developed in our lab (based on GMMs) by incorporating
spatial features obtained from classical source localization and
separation techniques (e.g. ICA, DUET, beamforming).
The proposed framework will be primarily applied to speaker segmentation
and separation, which is the task of finding out the structure of a
speech recording according to the question "who spoke when and where"
and to extract the signal of each speaker. The results will be evaluated
on meeting data recorded by small microphone arrays. Data from the NIST
meeting evaluation will be used along with data recorded at our lab in a
room dedicated to the exploration of future meeting environments.
--
Emmanuel Vincent
METISS Project
IRISA-INRIA
Campus de Beaulieu, 35042 Rennes cedex, France
Phone: +332 9984 7227 - Fax: +332 9984 7171
Web: http://www.irisa.fr/metiss/members/evincent/
From kbp at imm.dtu.dk Sat Feb 10 07:37:53 2007
From: kbp at imm.dtu.dk (Kaare Brandt Petersen)
Date: Sat, 10 Feb 2007 13:37:53 +0100 (MET)
Subject: Connectionists: New version of The Matrix Cookbook
Message-ID:
Dear Colleagues
(Apologies for multiple postings)
A new and updated version of The Matrix Cookbok is now available at
http://www.imm.dtu.dk/pubdb/views/edoc_download.php/3274/pdf/imm3274.pdf
The Matrix Cookbook is a desktop reference on identities, relations and
approximations regarding matrices. For instance differentiation of
determinants, results for multivariate gaussians, expectations of
general multivariate distributions, etc. More information at
http://matrixcookbook.com/
Best regards, Michael and Kaare
--
Kaare Brandt Petersen * http://2302.dk
From d.g.heinke at bham.ac.uk Fri Feb 9 12:25:36 2007
From: d.g.heinke at bham.ac.uk (Dietmar Heinke)
Date: Fri, 9 Feb 2007 17:25:36 +0000
Subject: Connectionists: Research workshop on computational modeling
Message-ID: <45CCAE90.3060308@bham.ac.uk>
Call for Attendance
This workshop is part of a series of published colloquia on 'Advances in
cognitive neuroscience', held at the Behavioural Brain Sciences Centre,
University of Birmingham. The general aim of the workshop is to bring
together leading international researchers either using computational
models, or collecting data directly relevant to models, to discuss the
current state of the art, and to evaluate new directions in in the
interaction between models and data.
Title: Closing the gap between neurophysiology and behaviour: A
computational modelling approach
Organiser: Dietmar Heinke
Location: Behavioural Brain Sciences Centre, University of Birmingham,
Birmingham, United Kingdom
Date: 31.May 2007 to 2.June 2007
Aims and Objective
At present modelling approaches range from "neurophysiological processes
in details and indifferent to whole-system behaviour" to "modeling a
broad range of behavioural data but oblivious to neurophysiological
details". However, in order to close the gap between neurophysiological
process and human behavior it may be necessary to connect both ends of
that spectrum, such as modelling a broad range of behavioral data
together with neurophysiological details. This workshop aims at
discussing ways of closing the gap, i.e. how to develop an integrative
approach, by bringing together computational modelling researchers from
different points of the spectrum. A number of internationally renowned
researchers have agreed to present a paper at this workshop (see
http://comp-psych.bham.ac.uk/workshop.htm for details).
Registration
For further inquiries and registration please email the conference
secretary, Elaine Fox e.fox at bham.ac.uk.
Please note that to cover our expenses we will charge a small
registration fee of ? 30 per day to be paid at arrival.
Satellite workshop
Please note that there will be also a satellite workshop with the title
"The method of computational modelling: A practical introduction". This
workshop aims to give postdocs and postgraduates with a background in
psychology a hands-on introduction to computational modelling (see
http://comp-psych.bham.ac.uk/sat_workshop.htm for details).
Dietmar Heinke
--
School of Psychology
University of Birmingham
Birmingham B15 2TT, UK
http://www.psychresearch.bham.ac.uk/dgheinke/
Phone: +44 121-414-4920
FAX: +44 121-414-4897
From nips2007publicity at msn.com Mon Feb 12 21:24:12 2007
From: nips2007publicity at msn.com (Sumit Basu)
Date: Mon, 12 Feb 2007 18:24:12 -0800
Subject: Connectionists: NIPS*2007 - Preliminary Call for Papers
Message-ID:
PRELIMINARY CALL FOR PAPERS -- NIPS*2007
Deadline for Paper Submissions: June 8, 2007
Submissions are solicited for the Twenty-First Annual meeting of an
interdisciplinary Conference (December 3-6) which brings together
researchers interested in all aspects of neural and statistical processing
and computation. The Conference will include invited talks as well as oral
and poster presentations of refereed papers. It is single track and highly
selective. Preceding the main Conference will be one day of Tutorials
(December 3), and following it will be two days of Workshops at
Whistler/Blackcomb ski resort (December 7-8).
Invited Speakers: To be announced.
Tutorial Speakers: To be announced.
Submissions: Papers are solicited in all areas of neural information
processing and statistical learning, including (but not limited to) the
following:
· Algorithms and Architectures: statistical learning algorithms,
neural networks, kernel methods, graphical models, Gaussian processes,
dimensionality reduction and manifold learning, model selection,
combinatorial optimization.
· Applications: innovative applications or fielded systems that use
machine learning, including systems for time series prediction,
bioinformatics, text/web analysis, multimedia processing, and
robotics.
· Brain Imaging: neuroimaging, cognitive neuroscience, EEG
(electroencephalogram), ERP (event related potentials), MEG
(magnetoencephalogram), fMRI (functional magnetic resonance imaging),
brain mapping, brain segmentation, brain computer interfaces.
· Cognitive Science and Artificial Intelligence: theoretical,
computational, or experimental studies of perception, psychophysics,
human or animal learning, memory, reasoning, problem solving, natural
language processing, and neuropsychology.
· Control and Reinforcement Learning: decision and control,
exploration, planning, navigation, Markov decision processes,
game-playing, multi-agent coordination, computational models of
classical and operant conditioning.
· Hardware Technologies: analog and digital VLSI, neuromorphic
engineering, computational sensors and actuators, microrobotics,
bioMEMS, neural prostheses, photonics, molecular and quantum
computing.
· Learning Theory: generalization, regularization and model selection,
Bayesian learning, spaces of functions and kernels, statistical
physics of learning, online learning and competitive analysis,
hardness of learning and approximations, large deviations and
asymptotic analysis, information theory.
· Neuroscience: theoretical and experimental studies of processing and
transmission of information in biological neurons and networks,
including spike train generation, synaptic modulation, plasticity and
adaptation.
· Speech and Signal Processing: recognition, coding, synthesis,
denoising, segmentation, source separation, auditory perception,
psychoacoustics, dynamical systems, recurrent networks, Language
Models, Dynamic and Temporal models.
· Visual Processing: biological and machine vision, image processing
and coding, segmentation, object detection and recognition, motion
detection and tracking, visual psychophysics, visual scene analysis
and interpretation.
Review Criteria: As in the last year, NIPS submissions will be reviewed
double-blind: the reviewers will not know the identities of the authors.
Submissions will be refereed on the basis of technical quality, novelty,
potential impact on the field, and clarity. There will be an opportunity
after the meeting to revise accepted manuscripts. We particularly encourage
submissions by authors new to NIPS, as well as application papers that
combine concrete results on novel or previously unachievable applications
with analysis of the underlying difficulty from a machine learning
perspective.
Submission Instructions: NIPS accepts only electronic submissions at
http://nips2007.confmaster.net
These submissions must be in PDF format. The Conference web site will accept
electronic submissions until midnight June 8, 2007, Pacific daylight time.
Demonstrations: There is a separate Demonstration track at NIPS. Authors
wishing to submit to the Demonstration track should consult the Conference
web site.
Program Committee:
Francis Bach (Ecole des Mines de Paris)
Michael Black (Brown University)
Nicolo Cesa-Bianchi (Università degli Studi di Milano)
Olivier Chapelle (Yahoo! Research)
Sanjoy Dasgupta (UC San Diego)
Virginia de Sa (UC San Diego)
David Fleet (University of Toronto)
Isabelle Guyon (ClopiNet)
Bert Kappen (University of Nijmegen)
Dan Klein (UC Berkeley)
Daphne Koller (Stanford) [Co-Chair]
Chih-Jen Lin (National Taiwan University)
Kevin Murphy (University of British Columbia)
William Noble (University of Washington)
Stefan Schaal (University of Southern California)
Dale Schuurmans (University of Alberta)
Odelia Schwartz (Salk Institute and Albert Einstein College of Medicine)
Fei Sha (UC Berkeley)
Yoram Singer (Google and Hebrew University) [Co-Chair]
Mark Steyvers (UC Irvine)
Alan Stocker (New York University)
Yee Whye Teh (Gatsby Unit, UCL)
Nikos Vlassis (Technical University of Crete)
Ulrike von Luxburg (MPI for Biological Cybernetics)
Chris Williams (University of Edinburgh)
Andrew Zisserman (University of Oxford)
Deadline for Paper Submissions: June 8, 2007
From hiro at brain.riken.jp Mon Feb 12 07:19:32 2007
From: hiro at brain.riken.jp (hiroyuki nakahara)
Date: Mon, 12 Feb 2007 21:19:32 +0900
Subject: Connectionists: CFA RIKEN BSI 2007 Summer School
Message-ID: <20070212211927.327D.HIRO@brain.riken.jp>
Dear colleagues,
I forward the following information.
- Hiro Nakahara
Call for Applications
RIKEN Brain Science Institute 2007 Summer Program
URL: http://www.brain.riken.jp/english/f_summ/f0_top.html
Application deadline; February 28th, 2007
Lecture Course: July 23 - August 3
Internship: July 4 - August 29
Every summer, RIKEN Brain Science Institute (Wako, Japan; nearby Tokyo)
organizes the international summer school. The short summary of the
summer school this year is attached below. Application guideline,
further information of the coming and past summer schools and etc are
on the above URL.
The summer school program has two types of applications. One is to
attend the lecture course (July 23 - August 3). The course has a a nice
mixture of experimental and theoeretical lectures. The other is to have
a two-months intership in one of laboratories at RIKEN Brain Science
Instiute in addition to the attendance at the lecture course. In both
types, financial support for travel and accommodation will be considered
for those without external funding.
For questions, please send any general inquiry not to me but to the
adminstration or organizing committee of the summer school on the
the summer school URL(http://www.brain.riken.jp/english/f_summ/f0_top.html),
while you can send inquiry to me if it is specifically about my
laboratory (lab URL: http://www.itn.brain.riken.jp/index_eng.html).
2007 Summer Program Title; Brain Science: Mystery and Mission
2007 is the 10th anniversary of RIKEN BSI. Coinciding with the early
years of the 21st century, this is a special occasion for celebrating
past achievements in brain science, as well as, importantly,
articulating the shape of the field in the decades to come. The theme of
this Summer Program, therefore, is deliberately broad. A roster of
international researchers will lecture on their area of expertise, and
join in considering new directions of brain science and its long-term
role in society. We hope students will gain further inspiration for
their own mystery and mission in the years ahead.
Invited Lecturers
Shun-ichi Amari (RIKEN BSI, Japan)
Terrence Deacon (UC Berkeley, USA)
John Donoghue (Brown University)
Aike Guo (Chinese Academy of Sciences, P.R. China)
Zhigang He (Children's Hospital, Boston, USA)
Masao Ito (RIKEN BSI, Japan)
Erich Jarvis (Duke University, USA)
Mitsuo Kawato (ATR, Japan)
Akihiro Kusumi (Kyoto University, Japan)
Klaus-Peter Lesch (Univ. of Wurzburg, Germany)
Pierre-Marie Lledo (Institut Pasteur, France)
Nikos Logothetis (MPI for Biological Cybernetics, Germany)
Katsuhiko Mikoshiba (RIKEN BSI, Japan)
Carol Mason (Columbia University, USA)
Klaus Obermayer (Bernstein Center for Computational Neuroscience Berlin,Germany)
Dennis O'Leary (Salk Institute)
Noriko Osumi (Tohoku University, Japan)
Josh Sanes (Harvard University, USA)
Keiji Tanaka (RIKEN BSI, Japan)
Charles Weissmann (Scripps Florida, USA)
George Yancopoulos (Regeneron Pharmaceuticals, Inc., USA)
---------------------------------
Hiro Nakahara
Lab for Integrated Theoretical Neuroscience
RIKEN Brain Science Institute
2-1 Hirosawa Wako
Saitama, 351-0198, Japan
Email: hn at brain.riken.jp
Lab webpage: http://www.itn.brain.riken.jp/index_eng.html
--
hiroyuki nakahara
http://www.itn.brain.riken.jp
From Johan.Suykens at esat.kuleuven.be Mon Feb 12 08:56:52 2007
From: Johan.Suykens at esat.kuleuven.be (Johan Suykens)
Date: Mon, 12 Feb 2007 14:56:52 +0100
Subject: Connectionists: Data Visualization and Dimensionality Reduction
Message-ID: <45D07224.8010205@esat.kuleuven.ac.be>
Dear Connectionists,
Please find enclosed a new technical report on data visualization and
dimensionality reduction,
together with a demo file.
Best regards,
Johan Suykens
J.A.K. Suykens, "Data Visualization and Dimensionality Reduction using
Kernel Maps with a Reference Point",
Internal Report 07-22, ESAT-SISTA, K.U. Leuven (Leuven, Belgium), Feb. 2007.
PDF: http://www.esat.kuleuven.ac.be/sista/lssvmlab/KMref/KMref0722.pdf
Matlab demo:
http://www.esat.kuleuven.ac.be/sista/lssvmlab/KMref/demoswissKMref.m
Abstract-
In this paper a new kernel based method for data visualization and
dimensionality reduction is proposed.
A reference point is considered corresponding to additional constraints
taken in the problem formulation.
In contrast with the class of kernel eigenmap methods, the solution
(coordinates in the low dimensional space)
is characterized by a linear system instead of an eigenvalue problem.
The kernel maps with a reference point
are generated from a least squares support vector machine core part that
is extended with an additional
regularization term for preserving local mutual distances together with
reference point constraints.
The kernel maps possess primal and dual model representations and
provide out-of-sample extensions
e.g. for validation based tuning. The method is illustrated on toy
problems and real life data sets.
Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm
From daniela.pelz at bccn-berlin.de Tue Feb 13 06:19:43 2007
From: daniela.pelz at bccn-berlin.de (Daniela Pelz)
Date: Tue, 13 Feb 2007 12:19:43 +0100
Subject: Connectionists: PhD Program and PhD scholarships in Computational
Neuroscience
Message-ID: <45D19ECF.4030605@bccn-berlin.de>
PhD program and PhD scholarships in Computational Neuroscience
Bernstein Center for Computational Neuroscience
Berlin, Germany
The Bernstein Center Berlin solicits applications for an international
PhD program in Computational Neuroscience (http://www.bccn-berlin.de).
The PhD program is full-time for three years, and will start in October
2007. Course language is English. There are no tuition fees and the
program offers a limited number of scholarships of up to ? 1800,- per
month initially for two years. The doctoral degree is awarded by the
department of the student?s principal thesis advisor. Successful
candidates additionally receive a certificate from the Bernstein Center
for Computational Neuroscience including a transcript of records.
Application deadline is March 15^th 2007 for full consideration.
Applications received after the deadline can however be considered until
the admission process is completed. Courses start in October 2007. For
application details see:
http://www.bccn-berlin.de/teaching/program/phd
Objective of the PhD Program
Computational neuroscience uses a multidisciplinary approach for
understanding the brain. It combines experiments with data analysis and
computer simulations on the basis of well-defined theoretical concepts
and makes a scientific language available that can be used across
disciplines and levels for neurobiology, cognitive science, and
information technology. Computational Neuroscience may thus help to
solve long-standing research questions, contribute to better prevention
and treatment strategies for neural disorders, lead to unified concepts
about biological processes, advance information technologies and
human-machine interactions, and, last but not least, provide new insight
for designing efficient strategies for teaching and learning.
The PhD program emphasizes a broad, interdisciplinary education with
strong interactions between experiment and theory. The programs? faculty
is drawn from the Bernstein Center for Computational Neuroscience, which
represents university departments ranging from biology and medicine to
physics and computer science at the three major universities in Berlin,
i.e. Humboldt Universit?t zu Berlin, Berlin Technical University, Freie
Universit?t Berlin, as well as Charit? Universit?tsmedizin Berlin.
Bernstein Center for Computational Neuroscience
The Bernstein Center for Computational Neuroscience Berlin integrates
research and teaching activities at the Charit?-Universit?tsmedizin
Berlin, Freie Universit?t Berlin, Humboldt-Universit?t zu Berlin, Berlin
University of Technology, Fraunhofer FIRST, the Max-Delbrueck-Center and
the Wissenschaftskolleg zu Berlin.
http:// www.bccn-berlin.de
For further information please contact daniela.pelz at bccn-berlin.de
--
Dr. Daniela Pelz
Teaching Coordinator
Bernstein Center for Computational Neuroscience
Humboldt University
Philippstr. 13 House 6
10115 Berlin
phone: (030) 2093-6773
fax: (030) 2093-6771
From cjlin at csie.ntu.edu.tw Tue Feb 13 09:48:48 2007
From: cjlin at csie.ntu.edu.tw (Chih-Jen Lin)
Date: Tue, 13 Feb 2007 22:48:48 +0800
Subject: Connectionists: two papers and one software for NMF
Message-ID:
Dear Colleagues,
We announce two papers and one software package
for Nonnegative Matrix Factorization (NMF).
Paper: Projected gradient methods for non-negative matrix
factorization. To appear in Neural Computation 2007.
http://www.csie.ntu.edu.tw/~cjlin/papers/pgradnmf.pdf
Abstract:
Non-negative matrix factorization (NMF) can be formulated as a
minimization problem with bound constraints. Although
bound-constrained optimization has been studied extensively in both
theory and practice, so far no study has formally applied its
techniques to NMF. In this paper, we propose two projected gradient
methods for NMF. The proposed methods exhibit strong optimization
properties. We discuss efficient implementations and demonstrate that
one of the proposed methods converges faster than the popular
multiplicative update approach. A simple MATLAB code is also
provided.
Software:
An fast implementation of the proposed method in the above paper is at
http://www.csie.ntu.edu.tw/~cjlin/nmf
Paper: On the convergence of multiplicative update algorithms for
non-negative matrix factorization. To appear in IEEE TNN 2007
http://www.csie.ntu.edu.tw/~cjlin/papers/multconv.pdf
abstract: Non-negative matrix factorization (NMF) is useful to find
basis information of non-negative data. Currently, multiplicative
updates are a simple and popular way to find the factorization.
However, for the common NMF approach of minimizing the Euclidean
distance between approximate and true values, no proof has shown that
that multiplicative updates converge to a stationary point of the NMF
optimization problem. Stationarity is important as it is a necessary
condition of a local minimum. This paper discusses the difficulty of
proving the convergence. We propose slight modifications of existing
updates and prove their convergence. Techniques invented in this
paper may be applied to prove the convergence for other
bound-constrained optimization problems.
Your comments are very welcome.
Best regards,
Chih-Jen Lin
Dept. of Computer Science
National Taiwan Univ.
From becker at mcmaster.ca Mon Feb 12 06:24:39 2007
From: becker at mcmaster.ca (S. Becker)
Date: Mon, 12 Feb 2007 06:24:39 -0500 (EST)
Subject: Connectionists: papers on hippocampal models of neurogenesis,
spatial cognition
Message-ID:
Dear colleagues, the following two articles may be of interest.
Becker, S. and Wojtowicz, J.M. (2007), A model of hippocampal neurogenesis
in memory and mood disorders. Trends in Cognitive Sciences 11(2):70-76.
Preprint:
http://www.science.mcmaster.ca/Psychology/becker/papers/BeckerWojtowiczTICSRevisedWFigs.pdf
Published article (Science Direct doi)
http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6VH9-4MK0J2K-1&_user=10&_coverDate=02%2F28%2F2007&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000050221&_version=1&_urlVersion=0&_userid=10&md5=0c36226a907589ea1999243d0e501d42
Byrne, P., Becker, S. and Burgess, N. (to appear), Remembering the past
and imagining the future: a neural model of spatial memory and imagery.
Psychological Review.
Preprint:
http://www.science.mcmaster.ca/Psychology/becker/papers/ByrneBeckerBurgess_SingleSpace.pdf
Sue Becker, Professor
Department of Psychology, Neuroscience & Behaviour
McMaster University
www.science.mcmaster.ca/Psychology/sb.html
From M.Casey at surrey.ac.uk Thu Feb 15 04:09:55 2007
From: M.Casey at surrey.ac.uk (M.Casey@surrey.ac.uk)
Date: Thu, 15 Feb 2007 09:09:55 -0000
Subject: Connectionists: Information Fusion Journal Special Issue: Extended
Deadline
Message-ID:
Due to a number of requests, we are currently still accepting papers for
the special issue of the journal Information Fusion on "Biologically
Inspired Information Fusion".
If you are currently intending to submit a paper then please contact the
guest editors as soon as possible. All extensions will be agreed on a
case-by-case basis.
Full details at http://www.elsevier.com/locate/inffus
Bringing together research on the biology and psychology of
multi-sensory processing, computational neuroscience and theoretical
work on mechanisms for combining different information sources.
Topics appropriate for this special issue include, but are not limited
to:
* Biologically inspired fusion schemes
* Adaptive information fusion which emphasize biological motivations
* Biologically inspired fusion in robotics
* Multimodal integration:
* Modeling combined sensory processing
* Including, but not exclusively, combining vision, audition,
olfaction, taste or touch
* Combining artificial and biological sensors
* Attention or emotional biasing on sensory processing
* Biologically motivated applications of multi-sensor integration
Our understanding of both natural and artificial cognitive systems is an
exciting area of research that is developing into a multi-disciplinary
subject with the potential for significant impact on science,
engineering and society in general. There is considerable interest in
how our understanding of natural systems may help us to apply biological
strategies to artificial systems. Of particular interest is our
understanding of how to build adaptive information fusion systems by
combining knowledge from different domains. In natural systems, the
integration of sensory information is learnt at an early stage of
development. Therefore, through a better understanding of the structures
and processes involved in this natural adaptive integration, we may be
able to construct a truly artificial multi-sensory processing system.
Here then, psychological and physiological knowledge of multisensory
processing, and particularly the low level influence that different
modalities have on one another, can be used to build upon existing
theoretical work on computational mechanisms, such as self organization
and the combination of multiple neural networks, to build systems that
can fuse together different information sources.
These themes were recently discussed at an International Workshop on
Biologically Inspired Information Fusion. As well as presenting the
state-of-the-art on multi-sensory processing and information fusion from
the life and physical sciences, the workshop provided a forum for
researchers to discuss priorities for developing this multi-disciplinary
area. This special issue of Information Fusion is therefore aimed at
following up from these discussions by focusing on the highlighted
priorities, whilst also providing an opportunity for the wider
dissemination of relevant themes. For this special issue, papers should
either have a biological motivation and/or inspiration, or otherwise be
of biological relevance and interest. Manuscripts should make the
biological dimension explicit. Information Fusion related papers lacking
this dimension are to be submitted to a regular issue of the journal.
Manuscripts (which should be original and not previously published or
presented even in a more or less similar form under any other forum)
covering biologically inspired information fusion methods and their
applications as well as the theories and algorithms developed to address
these applications are invited. Contributions should be described in
sufficient detail to be reproducible on the basis of the material
presented in the paper.
Manuscripts should be submitted electronically online at
http://ees.elsevier.com/inffus. The corresponding author will have to
create a user profile if one has not been established before at
Elsevier. Simultaneously, please also send without fail an electronic
copy (PDF format preferred), to the Guest Editors listed below. Please
identify clearly that the submission is meant for this special issue.
Guest Editors
Dr Matthew Casey, Department of Computing, University of Surrey, UK,
m.casey at surrey.ac.uk
Professor Robert Damper, School of Electronics and Computer Science,
University of Southampton, UK, rid at ecs.soton.ac.uk
Further information can be found at:
http://www.cs.surrey.ac.uk/people/academic/M.Casey/biif2006.html
http://www.elsevier.com/authored_subject_sections/P05/pdf/cfp_bif.pdf
http://www.elsevier.com/locate/inffus
From amirhussain007 at aol.com Thu Feb 15 10:10:50 2007
From: amirhussain007 at aol.com (Dr. Amir Hussain)
Date: Thu, 15 Feb 2007 15:10:50 -0000
Subject: Connectionists: 2nd Call for Papers for 17th ICANN 2007, Porto,
Portugal, 9-13 Sep 2007
Message-ID: <001601c75113$7b5476f0$0200a8c0@cs.ad.stir.ac.uk>
Please forward the Call below to friends and colleagues...
Thank you in advance and please accept our apologies for any
cross-postings..
Kind regards,
Amir Hussain, PhD
Centre for Cognitive & Computational Neuroscience
University of Stirling
Scotland, UK
Email: ahu at cs.stir.ac.uk
--------------------
International Conference on Artificial Neural Networks - ICANN 2007
9-13 September 2007, Ipanema Park Hotel, Porto, Portugal
Web page: http://www.icann2007.org
2nd Call for Papers
Deadlines
16 Feb End of submission of special session and workshop proposals.
23 Mar End of submission of full papers.
The 17th International Conference on Artificial Neural Networks, ICANN
2007,
will be held from September 9 through September 13 at the Ipanema Park
Hotel, Porto, Portugal. ICANN is an annual conference organized by the
European Neural Network Society in co-operation with the International
Neural Network Society, and is a premier event in all topics related to
neural networks.
ICANN 2007 welcomes contributions on the theory, algorithms and
applications in the following broad areas:
- Computational neuroscience;
- Connectionist cognitive science;
- Data analysis and pattern recognition;
- Graphical network models, Bayesian networks;
- Hardware implementations and embedded systems;
- Intelligent Multimedia and the Semantic Web;
- Neural and hybrid architectures and learning algorithms;
- Neural control, planning and robotics applications;
- Neural dynamics and complex systems;
- Neuroinformatics;
- Real world applications;
- Self-organization;
- Sequential and structured information processing;
- Signal and time series processing, blind source separation;
- Vision and image processing.
General-Chair
Joaquim Marques de S?, University of Porto, Portugal
Co-Chair
Lu?s Alexandre, University of Beira Interior, Portugal
Program Chairs
Wlodzislaw Duch, Torun, PL & Singapore, ENNS President
Danilo Mandic, Imperial College London, UK
Honorary Chair
John G. Taylor, Kings College, London, UK
Program Committee
Alessandro Sperduti, Univ. Padova, IT
Alessandro Villa, Univ. Grenoble, FR
Amir Hussain, University of Stirling, UK
Andreas Nuernberger, Univ. Magdeburg, DE
Andreas Stafylopatis, NTUA, GR
Andrzej Cichocki, RIKEN Brain Sci. Inst., JP
Bruno Apolloni, Univ. Milano, IT
David Miller, Univ. Pennsylvania, USA
Dragan Obradovic, Siemens Corp. Res., DE
Erkki Oja, Helsinki University, FI
Erol Gelenbe, Imperial College London, UK
Hojjat Adeli, Ohio State Univ., USA
Jacek Mandziuk, Warsaw University, PL
Jo?o Lu?s Rosa, Catholic Univ. Campinas, BR
Jose Dorronsoro, Univ. Aut. de Madrid, ES
Jos? Pr?ncipe, Univ. Florida, USA
Juergen Schmidhuber, TU Munich (DE) and IDSIA (CH)
Lefteris Tsoukalas, Purdue Univ., USA
Marios Polycarpou, Univ.Cyprus, CY
Mark Embrechts, Rensselaer Inst., USA
Michel Verleysen, Univ. Louvain-la-Neuve, BE
Nikola Kasabov, Auckland Univ., NZ
Okyay Kaynak, Bogazici University, TR
Olli Simula, Helsinki University, FI
Peter Andras, Univ. Newcastle, UK
P?ter ?rdi, HU & Kalamazoo College, USA
Stan Gielen, University of Nijmegen, NL
Stefan Wermter, Univ.Sunderland, UK
Stefanos Kolias, NTUA, GR
Steve Gunn, Univ. Southampton, UK
Thomas Martinetz, Univ. Luebeck, DE
Conference Proceedings
Published by Springer-Verlag (Lecture Notes in Computer Science).
Neural Networks Special Issue
An extended version of selected ICANN 2007 papers will be published in a
Special Issue of Elsevier's journal Neural Networks.
Sponsors: ENNS, INNS, JNNS, EURASIP, IEEE-CIS, MICROSOFT, INEB, ISEP,
UBI
Student support available (please see web page)
ICANN 2007 Secretariat
Gabriela Afonso, INEB, Campus FEUP, Rua Dr. Roberto Frias, Porto,
Portugal
(gafonso at fe.up.pt)
From pascal.fua at epfl.ch Thu Feb 15 13:57:05 2007
From: pascal.fua at epfl.ch (pascal.fua@epfl.ch)
Date: Thu, 15 Feb 2007 19:57:05 +0100
Subject: Connectionists: Opening for a PhD candidate in Computer Vision at
EPFL
Message-ID: <1171565825.45d4ad0128597@imapwww.epfl.ch>
EPFL?s computer vision lab (http://cvlab.epfl.ch/) has an opening for a PhD
candidate interested in working on 3D shape and motion recovery from video.
For details about our research activities, see
http://cvlab.epfl.ch/research/research.html. For practical information about
EPFL?s doctoral program and life in Lausanne, see
http://acide.epfl.ch/doc-cr/phdguide.pdf.
Education:
Masters degree in Computer Science or related field with experience in the areas
of Computer Vision or Computer Graphics. A strong background in Mathematics is
desirable.
Applying:
1. Apply to our doctoral program, as explained under
http://phd.epfl.ch/page55508.html.
2. Specify in the application form that you are interested by Prof. Fua?s CVLab.
There is no need to contact him directly.
From ale at sissa.it Fri Feb 16 11:10:25 2007
From: ale at sissa.it (Alessandro Treves)
Date: Fri, 16 Feb 2007 17:10:25 +0100
Subject: Connectionists: EBBS 2007 student travel awards
Message-ID: <1171642225.45d5d771928ed@webmail.sissa.it>
The European Brain and Behaviour Society offers 10 student fellowships of
? 500,- each to attend its 39th Meeting in Trieste, September 15-19, 2007.
Award recipients will be required to present a poster.
The award winners will be announced on the web-site by the end of June.
The awards will be presented at the Conference Banquet on Tuesday evening.
Winners will receive the cash award, a certificate and the banquet fees.
Who can apply? EBBS members at the time of registration for the meeting.
? 8 awards: PhD students (EBBS student membership, ? 20)
? 2 awards: post-docs within two years after the thesis (regular, ? 40)
To apply for the travel awards, DEADLINE April 1st, 2007, and to apply for
EBBS (student) membership: please, see instructions on www.ebbs-science.org
Information about the meeting is on http://people.sissa.it/~ale/EBBS2007
--
Alessandro Treves
SISSA - Cognitive Neuroscience, now downtown in via Stock 2/2, V fl.
BUT NOTE, POSTAL ADDRESS: SISSA - via Beirut 2, 34014 Trieste, Italy
tel:39-040-3787623 fax:39-040-3787615 http://people.sissa.it/~ale/
----------------------------------------------------------------
SISSA Webmail https://webmail.sissa.it/
Powered by Horde http://www.horde.org/
From emmanuel.vincent at irisa.fr Fri Feb 16 12:47:36 2007
From: emmanuel.vincent at irisa.fr (Emmanuel Vincent)
Date: Fri, 16 Feb 2007 18:47:36 +0100
Subject: Connectionists: Stereo Audio Source Separation Evaluation Campaign:
CALL FOR PARTICIPATION
Message-ID: <45D5EE38.9090006@irisa.fr>
*** SECOND CALL FOR PARTICIPATION ***
1st Stereo Audio Source Separation
Evaluation Campaign
http://sassec.gforge.inria.fr/
Participation deadline: April 13, 2007
Do you have an algorithm for source separation from few channels? Or are
you interested in this challenging issue? Then you should take part in
the first campaign for the evaluation of stereo audio source separation
algorithms.
The task is to estimate from a two-channel speech or music mixture the
contribution of each source on each channel, the number of sources being
equal to three or more. This campaign complements recent evaluation
initiatives conducted by Lucas Parra and the PASCAL network, which
focused on different numbers of sources and channels.
Three types of mixtures are considered:
- instantaneous mixtures,
- synthetic convolutive mixtures,
- live recordings.
All contributions are welcome, including established, novel, blind,
non-blind, two-channel or single-channel algorithms. The evaluation will
be non-competitive: the results will be made available on the campaign
website for listening and evaluated using multiple criteria, possibly
proposed by the participants. The results will be summarized in a paper
to be discussed at the ICA'07 conference (see http://www.ica2007.org/),
during which the participants who wish to present a poster about their
algorithm will also have the opportunity to do so. These posters will
then be published on the campaign website.
For more information about the campaign and to download development/test
sets and evaluation criteria, see
http://sassec.gforge.inria.fr/
Best regards,
Emmanuel Vincent, Hiroshi Sawada, Pau Bofill, Shoji Makino and Justinian
Rosca
From tmatsui at ism.ac.jp Fri Feb 16 16:06:02 2007
From: tmatsui at ism.ac.jp (Tomoko Matsui)
Date: Sat, 17 Feb 2007 06:06:02 +0900
Subject: Connectionists: postdoc opportunity
Message-ID: <20070217060424.EA5B.TMATSUI@ism.ac.jp>
This is an announcement for a job opportunity for a postdoc in the
Institute of Statistical Mathematics (ISM), Research Organization of
Information and Systems (ROIS).
----------------------------------
JOB OPPORTUNITY
Postdoctoral position:
Applicants are invited to apply to the Transdisciplinary Research
Integration Center, ISM/ROIS. ISM is one of member institutes of ROIS
along with the National Institute of Informatics, the National Institute
of Genetics and the National Institute of Polar Research. The ISM
mission includes promoting statistical science and developing an
innovative methodology for approaching complex problems related to life
science, earth science, environmental science and human sciences from
the view point of information and systems
(http://www.ism.ac.jp/index_e.html). The position will start as soon as
possible after 1 April 2007. The postdoctoral researcher will work on
the following project ?Discovery of Invariants in Multimodal Data?
(http://www.ism.ac.jp/~tmatsui/kinou2_p4/index-en.html). The initial
contract is one-year long but could be extended up to three years.
Field of work:
Machine learning, kernel machines, computational statistics,
Bayesian statistics, or multimodal processing
Project description:
Multimodal data available to us through the Internet and other
electronic media are explosively increasing both in number and in
variety. To handle such massive data for various purposes, new
technologies need to be developed. With this in mind, we have started
investigating a new methodology that allows us to discover from
multimodal data the information relevant to the purpose at hand (which
is referred to as ?invariants?). To achieve this goal, we will study
several qualitatively different problems from different research areas,
in which multimodal data play a central role (e.g., visual/audio/text
processing, cognitive science, auditory perception and robotics). The
problems are to be tackled with some of the recently developed inductive
learning machines including automatic model selection mechanism (e.g.,
Penalized Logistic Regression Machines and Support Vector Machines). The
results will be analyzed in order to establish a new methodology for
discovery of invariants, which will be applicable to problems across
different areas of study.
Job description:
The successful candidate will support and coordinate our efforts in
the area of investigation of methods for discovery of invariants with
multimodal data.
Requirements:
Applicants should have a PhD and some knowledge of machine learning
and statistics. Applicants must be able to program (C/C++ and Matlab
knowledge is an advantage but not requirement) and must also have
experience with statistical data analysis.
Payment:
The salary will be in the range of 4,500,000 yen - 6,000,000 yen
(before tax and insurance).
Application:
Applicants should send their CV, including a list of publications
and the names of two potential referees.
Contact:
Prof. Tomoko Matsui
E-mail: tmatsui at ism.ac.jp
Tel: +1 604 822 9662 (until 9 March 2007 (Vancouver, Canada))
+81 3 5421 8769 (from 10 March 2007 (Japan))
----------------------------------
--
Tomoko Matsui
The Institute of Statistical Mathematics
Tel: +81 3 5421 8769 Fax: +81 3 5421 8796
E-mail: tmatsui at ism.ac.jp
HP: http://www.ism.ac.jp/~tmatsui/
From shipeng.yu at siemens.com Mon Feb 19 16:50:01 2007
From: shipeng.yu at siemens.com (Yu, Shipeng (MED US))
Date: Mon, 19 Feb 2007 16:50:01 -0500
Subject: Connectionists: Internship available at Siemens Medical Solutions
USA
Message-ID: <6E67E19DB8BFD743A688D8A6F82C02B101BDA031@USMLVV1EXCTV03.ww005.siemens.net>
*Apologies for cross posting. Please forward to interested people*
The Computer-Aided Diagnosis Group at Siemens Medical Solutions USA is
looking for summer interns. We are specifically interested in motivated
Ph.D. students in diverse areas of machine learning, data mining and
natural language processing.
Siemens Medical Solutions is one of the largest global suppliers of
healthcare equipment, renowned for innovative products, services and
solutions including diagnostic imaging systems, therapy equipment,
electromedicine, and IT solutions to optimize workflow and increase
efficiency in the healthcare industry. The CAD group is committed to
building a world-class R&D team in machine learning and data mining.
As an intern, you will join CAD's team of scientists in solving exciting
and challenging research problems in the medical field. Our research is
motivated by decision-support and data processing problems arising in
the
medical domain and related health areas; experience or interest in these
areas is a plus. Our team currently conducts research in Bayesian
methods,
probabilistic inference, statistical learning theory, optimization,
statistics, natural language processing, data mining and works closely
with a team of image processing scientists.
You will be expected to spend at least 10-12 weeks; however there is
much
flexibility in the starting and finishing dates (non-summer and longer
internships are also considered). We provide competitive salaries and
also
strongly encourage all interns to publish.
In order to apply, please follow these steps:
* Email your CV to the address below
* Request one letter of recommendation (preferably from your advisor)
to
be emailed to us
* Briefly (e.g., in half a page) tell us about what research and
application areas you would prefer to work on and during what dates
you
wish to join
Email the above to shipeng.yu siemens.com, with the subject "CAD ML
Internships". Please also send emails if you need further information
about the internships.
We are located in Malvern, PA, approximately one hour from Center City
Philadelphia, on the suburban Main Line area.
----------------------------------------------------------
Shipeng Yu, Ph.D.
Staff Scientist
Siemens Medical Solutions, MS E51
Computer Aided Diagnosis & Therapy
51 Valley Stream Parkway
Malvern, PA 19355 USA
Email: shipeng.yu at siemens.com
Office: 610-448-4420
Fax: 610-448-4274
----------------------------------------------------------
----------------------------------------------------------------------------
This message and any included attachments are from Siemens Medical Solutions
and are intended only for the addressee(s).
The information contained herein may include trade secrets or privileged or
otherwise confidential information. Unauthorized review, forwarding, printing,
copying, distributing, or using such information is strictly prohibited and may
be unlawful. If you received this message in error, or have reason to believe
you are not authorized to receive it, please promptly delete this message and
notify the sender by e-mail with a copy to Central.SecurityOffice at siemens.com
Thank you
From astrid.prinz at emory.edu Mon Feb 19 17:44:05 2007
From: astrid.prinz at emory.edu (Astrid Prinz)
Date: Mon, 19 Feb 2007 17:44:05 -0500
Subject: Connectionists: Postdoctoral position in computational neuroscience
Message-ID: <20070219174405.rvsrtmdjgoco0k8w@webmail.service.emory.edu>
Postdoctoral position in computational neuroscience
Emory University, Atlanta
We are looking for a highly motivated postdoctoral researcher to
study homeostatic plasticity in neurons and neuronal circuits through
a combination of modeling and experimentation. The ideal candidate has
a strong background in neuroscience and computer modeling, and
experience with electrophysiology is very desirable. The position is
available immediately, and further information on the lab is located
at http://www.biology.emory.edu/research/Prinz/index.html. To
apply, please submit a CV, description of research interests, and two
letters of reference to astrid.prinz at emory.edu or to Astrid Prinz
Department of Biology, Emory University
O. Wayne Rollins Research Center
1510 Clifton Road
Atlanta, GA 30322
From Yann.Guermeur at loria.fr Wed Feb 21 08:53:29 2007
From: Yann.Guermeur at loria.fr (Yann Guermeur)
Date: Wed, 21 Feb 2007 14:53:29 +0100
Subject: Connectionists: Special session ASMDA'07 : Extended deadline
Message-ID: <45DC4ED9.3090408@loria.fr>
Dear Colleagues,
Due to many requests, the deadline to submit a paper to the special
session "Supervised Prediction with Neural Networks and SVMs" :
http://www.loria.fr/~guermeur/ASMDA_CFP.html
of the ASMDA'07 international conference is extended to March, 1st 2007.
Best regards,
Yann Guermeur
--
Yann Guermeur Tel: (+33) 03 83 59 30 18
LORIA Fax: (+33) 03 83 41 30 79
Campus Scientifique
BP 239
54506 Vandoeuvre-les-Nancy Cedex email: Yann.Guermeur at loria.fr
FRANCE http://www.loria.fr/~guermeur
From ted.carnevale at yale.edu Thu Feb 22 14:45:41 2007
From: ted.carnevale at yale.edu (Ted Carnevale)
Date: Thu, 22 Feb 2007 14:45:41 -0500
Subject: Connectionists: NEURON 2007 Summer Course
Message-ID: <45DDF2E5.9060307@yale.edu>
COURSE ANNOUNCEMENT
What:
"The NEURON Simulation Environment"
(NEURON 2007 Summer Course)
http://www.neuron.yale.edu/neuron/sdsc2007/sdsc2007.html
When:
Saturday, June 23, through Wednesday, June 27, 2007
Where:
The Institute for Neural Computation
at the University of California, San Diego, CA
Organizers:
N.T. Carnevale and M.L. Hines
Description:
This intensive hands-on course covers the design, construction,
and use of models in the NEURON simulation environment. It is
intended primarily for those who are concerned with models of
biological neurons and neural networks that are closely linked
to empirical observations, e.g. experimentalists who wish to
incorporate modeling in their research plans, and theoreticians
who are interested in the principles of biological computation.
The course is designed to be useful and informative for registrants
at all levels of experience, from those who are just beginning
to those who are already quite familiar with NEURON or other
simulation tools.
Registration is limited to 20, and the deadline for
receipt of applications is Monday, June 4, 2007.
For more information see
http://www.neuron.yale.edu/neuron/sdsc2007/sdsc2007.html
or contact
Ted Carnevale
Psychology Dept.
PO Box 208205
Yale University
New Haven, CT 06520-8205
USA
phone 203-494-7381
fax 203-432-7172
email ted.carnevale at yale.edu
Supported in part by:
National Institutes of Health
National Science Foundation
Institute for Neural Computation http://inc.ucsd.edu/
Contractual terms require inclusion of the following statement:
This course is not sponsored by the University of California.
--Ted
From bhanupvsr at gmail.com Thu Feb 22 19:18:10 2007
From: bhanupvsr at gmail.com (Bhanu Prasad)
Date: Thu, 22 Feb 2007 19:18:10 -0500
Subject: Connectionists: Special session on Neuroinformatics
Message-ID: <621812f80702221618t16dd1976t6e831d19e65f74b7@mail.gmail.com>
Call for papers
The 3rd Indian International Conference on Artificial Intelligence
(IICAI-07) (website: http://www.iiconference.org is offering a special
session on *Neuroinformatics*. The topics of interest include but will not
be limited to
- Neuroscience data and knowledge bases
- Analytical and modelling tools and techniques for neural data
analysis
- Computational models of brain function at multiple levels (from
molecular and all the way to behavioral)
The webpage: http://www.iiconference.org/iicai07/neuroinformatics.html
contains
more details of this session. The session/conference will be held in Pune,
India during December 17-19 2007. Also you may visit
http://www.iiconference.org for more information on the conference.
Bhanu Prasad
IICAI-07 Chair
Department of Computer and Information Sciences
Florida A&M University, Tallahassee, FL 32307, USA
Email: bhanupvsr at gmail.com
Phone: 850-412-7350
From bdbryant at cse.unr.edu Fri Feb 23 04:06:06 2007
From: bdbryant at cse.unr.edu (Bobby D. Bryant)
Date: Fri, 23 Feb 2007 01:06:06 -0800
Subject: Connectionists: GRAships - neuroevolution for agent control
Message-ID: <1172221566l.16120l.2l@localhost>
I have two Graduate Research Assistantships in the Department of
Computer Science and Engineering at the University of Nevada, Reno, for
work using neuroevolution to create "brains" for autonomous intelligent
agents that operate in the rich environments of videogames and computer
simulators.
The GRAs will pursue methods, applications, analysis, or theory in that
area. Opponent modelling and policy induction from human-generated
examples are of particular interest.
My colleague Sushil Louis has an additional GRAship in his Evolutionary
Computation Systems Laboratory. This GRA will pursue similar topics,
though not necessarily with ANNs.
Students who come to UNR will also have the opportunity to interact
with other professors and students who research computational
intelligence methods for human-computer interaction, robotics, vision,
and security. We are currently bootstrapping additional
interdisciplinary research programs with our colleagues in software
engineering, for the role of CI methods in game engine design, and in
psychology, for formal analysis of the behavior of autonomous
intelligent agents in rich environments.
Application instructions for our graduate program can be found at
http://www.unr.edu/content/programs/gradprograms.asp
The application deadline for the fall semester is April 15. If you
wish to be considered for the university's fellowship competition,
please apply by March 15. Either way, drop me a line when you have
submitted your application so I will know to expect it.
For background on the methods I have been using for agent control, see
the papers available at http://www.cse.unr.edu/~bdbryant/
For more information about the work in Dr. Louis's ECSL, see
http://ecsl.cse.unr.edu/
For the Department of Computer Science and Engineering, see
http://www.cse.unr.edu/
For the University of Nevada at Reno, http://www.unr.edu/
--
Bobby Bryant
Computational Intelligence / Computer Game Engineering
Department of Computer Science & Engineering
University of Nevada, Reno
From m.montemurro at manchester.ac.uk Mon Feb 26 08:07:47 2007
From: m.montemurro at manchester.ac.uk (Marcelo Montemurro)
Date: Mon, 26 Feb 2007 13:07:47 +0000
Subject: Connectionists: Manchester Neural Coding Workshop
Message-ID:
Dear all,
we are pleased to invite you to attend the Manchester Neural
Coding Workshop. The event will bring together a number of
leading international speakers to present cutting edge research
on neural coding from a multidisciplinary perspective.
The date, time and venue for the workshop are as follows:
26 March 2007, from 10:30 to 17:30
The University of Manchester
Faculty of Life Sciences
Moffat Building, Altrincham St, Lecture Theatre
Further details and travel information can be found at
http://www.manchester.ac.uk/lifesciences/neuralcodingworkshop
Registration and attendance are free. Please, send and email to
neuralcoding at gmail.com in order to register for complimentary buffet
lunch.
Invited speakers
* G. Indiveri
* N. K. Logothetis
* C. Petersen
* R. Q. Quiroga
* J. Schnupp
* J. Victor
Some travel support is available for participants traveling within the
UK (priority will be given to PhD students and postdocs).
Regards,
Marcelo Montemurro
Stefano Panzeri
Rasmus Petersen
--
Dr. Marcelo A. Montemurro
Faculty of Life Sciences
University of Manchester
Jackson's Mill, G7
PO Box 88
Sackville St
Manchester
M60 1QD
United Kingdom
phone : +44(0)161 306 3883
fax : +44(0)161 306 3887
e-mail: m.montemurro at manchester.ac.uk
From agutierrez at el.ub.es Tue Feb 27 04:11:44 2007
From: agutierrez at el.ub.es (agutierrez@el.ub.es)
Date: Tue, 27 Feb 2007 10:11:44 +0100
Subject: Connectionists: Post-doctoral position at the University of
Barcelona
Message-ID: <20070227101144.lgee42xiecc8wgcw@webmail.el.ub.es>
Post-doctoral position
The Intelligent Signal Processing group at the University of Barcelona
is looking for a Post-doctoral candidate to conduct research in the
area of biologically inspired signal processing for the following 3
years. The funding for this position will be provided by the Culture
and Science Ministry of Spain after the candidate passes a national
selection process.
Research
The position will involve research on the area of biologically
inspired processing mechanisms applied to machine olfaction. The study
and modeling of the olfactory system can provide new mechanisms to
process the chemical information provided by a matrix of non-specific
gas sensors.
Requirements
Due to the interdisciplinary nature of the research to be conducted,
candidates of multiple backgrounds will be considered, including:
Electronics, Signal processing, chemometrics, neural networks, neural
computation, and modeling of neural systems. A perfect candidate for
this position would be familiar with all this subjects. The candidate
is required to have a PhD title obtained before 30th of June 2007 and
later than 15th March 2004. So PhD students about that are about to
finish are eligible.
Funding
Juan de la Cierva program: This program provides funding for early
stage post-doctoral researchers (max. 3 years after obtention of PhD)
to work along with a consolidated research group in Spain. The work of
the post-doctoral researcher has to be associated to an on-going,
previously funded, project of the research group. The annual salary is
of 24.750 ? and the duration of the fellowship of 3 years. The
position will be starting around December 2007. More information at
(http://wwwn.mec.es/ciencia/jsp/plantilla.jsp?area=delacierva_eng&id=2)
Group
The Intelligent Signal Processing (ISP) group at the Universitat de
Barcelona is currently composed by 14 members: 2 associate professors,
2 postdoctoral scholars, 8 PhD students, and 2 graduate students. Four
additional associate professors cooperate in a regular basis with the
ISP group (http://isp.el.ub.es).
Application
Send a CV and a short list of research interests to Dr. Santiago Marco
(santi at el.ub.es) and Dr. Agust?n Gutierrez (agutierrez at el.ub.es)
IMPORTANT: Deadline 15th of March for the submission of the documents
to the Spanish Ministry. Contact us at least 10 days before that
deadline (by the 5th) to prepare the documentation.
--------------------------------------------------------------------------------
Agust?n Guti?rrez, PhD
Departament d'Electronica
Universitat de Barcelona
Mart? i Franqu?s 1
08028-Barcelona
Phone: +34 93 4039174
Fax: +34 93 4021148
--------------------------------------------------------------------------------
From rhaschke at techfak.uni-bielefeld.de Wed Feb 28 03:34:58 2007
From: rhaschke at techfak.uni-bielefeld.de (WSOM 2007)
Date: Wed, 28 Feb 2007 09:34:58 +0100
Subject: Connectionists: WSOM07 - 2nd Call for Papers
Message-ID: <45E53EB2.9030205@techfak.uni-bielefeld.de>
***********************************************************
2nd C A L L F O R P A P E R S
6th Int. Workshop on Self-Organizing Maps (WSOM 2007)
September 3rd - 6th 2007, Bielefeld, Germany
http://www.wsom07.org
***********************************************************
The conference website is open for submissions.
-- Important Dates --
Manuscript Submission 15th April 2007
Acceptance Notification 8th June 2007
Camera Ready Submission 1st July 2007
Early Registration 15th July 2007
Conference 3rd - 6th Sep 2007
-- About The Workshop --
The 6th International Workshop on Self-Organizing Maps will bring
together researchers and practicioners in the field of self-organizing
systems, with a particular emphasis on neural networks and
self-organizing maps. It will highlight key advances in these and
related fields. It is the sixth conference in a series of bi-annual
international conferences started with WSOM'97 in Helsinki.
The programme committee cordially invites you to attend WSOM 2007 and
submit papers on all aspects of self-organizing systems including:
* Self-organization
* Unsupervised learning
(including PCA/NLPCA, ICA/NLICA, Principal Curves/Surfaces)
* Signal processing, image processing and vision
* Robotics and Intelligent Systems
* Data visualization, mining and sonification
* Bioinformatics
* Text and document analysis
* Financial analysis
* Time-series analysis
* Theory and extensions
* Optimization
* Hardware and architecture
Papers will be peer reviewed by an international program committee
according to the criteria pertinence, scientific quality, impact,
generality, and innovation. High-quality submissions will be selected
for oral or poster presentation during the conference.
The conference programme will include invited talks as well as oral and
poster presentations of selected papers. It will be enriched by official
workshops to allow practitioners and scientists to discuss focussed
topics in an atmosphere that fosters the exchange of ideas.
Besides the scientific goals of the conference, the organisers strive to
provide an accessible meeting by keeping expenses for participants
affordable, particularly for young researchers.
-- Programme Committee --
Prof. Nigel Allinson (University of Sheffield, UK)
Prof. Marie Cottrell (Samos-Matisse Paris, France)
Prof. Erkki Oja (Helsinki University of Technology, Finland)
Prof. Helge Ritter (Bielefeld University, Germany)
Prof. Takeshi Yamakawa (Kyushu Institute of Technology, Japan)
Prof. Hujun Yin (UMIST Manchester, UK)
Dr. Barreto, Guilherme (Federal University of Ceara, Brazil)
Prof. Estevez, Pablo (University of Chile, Santiago)
Dr. Flanagan, Adrian (Nokia Research Center, Finland)
Prof. Furukawa, Tetsuo (Kyushu Institute of Technology, Japan)
Prof. Fyfe, Colin (University of Paisley, UK)
Prof. Hammer, Barbara (Clausthal University of Technology, Germany)
Prof. van Hulle, Marc (KU Leuven, Belgium)
Prof. Ishikawa, Masumi (Kyushu Inst. of Technology, Japan)
Prof. Kaski, Samuel (Helsinki University of Technology, Finland)
Prof. Lampinen, Jouko (Helsinki University of Technology, Finland)
Prof. Martinetz, Thomas (University of L?beck, Germany)
Prof. Miikkulainen, Risto (University of Texas at Austin, USA)
Prof. Pag?s, Gilles (University of Paris, France)
Dr. Polani, Daniel (University of Hertfordshire, UK)
Prof. Simula, Olli (Helsinki University of Technology, Finland)
Prof. Torras, Carme (University of Catalonia, Spain)
Prof. Ultsch, Alfred (University of Marburg, Germany)
Prof. Verleysen, Michel (Universit? catholique de Louvain, Belgium)
Dr. Villmann, Thomas (University of Leipzig, Germany)
Prof. Wermter, Stefan (University of Sunderland, UK)
-- Special Issue --
The best papers of the conference will be selected for a reviewed
special issue of a renowned scientific journal. More specific
information will be provided soon. Please watch our website.
-- Workshops --
The WSOM07 conference committee cordially invites members of the
community to submit proposals for workshops to be held in conjunction
with the main conference. Workshops should facilitate a lively
discussion about emerging topics or specific aspects in the area of
self-organizing systems. If you have any questions regarding workshop
topics or organisation, please feel free to contact the conference
office via email at info at wsom07.org or have a look at the conference
website for further information.
-- Instructions for Authors --
Prior to the submission deadline, please connect to the conference web
server to enter the title, author names and addresses, abstract and
keyword. The paper will then be assigned a paper identification number.
Full papers must be submitted according to the style guidelines
published on the conference website.
For further and updated information, please visit the conference website
http://www.wsom07.org
-- Organizing Committee --
Honorary Conference Chair
Prof. Teuvo Kohonen (Helsinki University of Technology)
General Conference Chair
Helge Ritter (Bielefeld University, Germany)
Steering Committee
Nigel Allinson (UMIST, Manchester, UK)
Marie Cottrell (SAMOS-MATISSE, Paris 1, France)
Erkki Oja (Helsinki Univ. of Tech., Finland)
Helge Ritter (Bielefeld University, Germany)
Takeshi Yamakawa (Kyushu Inst. of Tech., Japan)
Hujun Yin (UMIST, Manchester, UK)
Local Chair
Robert Haschke (Bielefeld University, Germany)
-- Enquiry and Information --
WSOM 2007 Conference Secretariat
Neuroinformatics Group
Bielefeld University, Germany
http://www.wsom07.org/contact.html
Email: info at wsom07.org
--
Int. Workshop on Self-Organizing Maps 3rd-6th September 2007
http://www.wsom07.org Bielefeld, Germany
Robert Haschke, Bielefeld University, Germany
_______________________________________________
robotics-worldwide mailing list
robotics-worldwide at usc.edu
http://duerer.usc.edu/mailman/listinfo/robotics-worldwide
From agutierrez at el.ub.es Wed Feb 28 04:54:18 2007
From: agutierrez at el.ub.es (agutierrez@el.ub.es)
Date: Wed, 28 Feb 2007 10:54:18 +0100
Subject: Connectionists: Book on bioinspired signal processing. Call for
contributions
Message-ID: <20070228105418.4blbw3qv28o8cs88@webmail.el.ub.es>
CALL FOR CONTRIBUTIONS
Book on Bioinspired Signal Processing
"Biologically inspired signal processing for chemical sensing"
Springer
We are preparing a book that will contain, but is not limited to,
selected articles based on the work presented at the Workshop on
Bioinspired Signal Processing held in Barcelona last January. The book
is entitled "Biologically inspired signal processing for chemical
sensing" and will be published in the book series Studies in
Computational Intelligence available from Springer.
We encourage you to submit your work as a full paper to be considered
for publication in the book. Researchers that did not participate on
the workshop are equally encouraged to submit their work. Articles
received from both workshop and non-workshop participants will equally
undergo a peer reviewed process.
Submission deadline: 30th April, 2007
Submit to: Dr. Santiago Marco (gospel_bsp at el.ub.es)
Minimum page size: 18 pages (in the format specified below)
Format: Word file. Format specified at www.gospel-wbsp-2007.org
--------------------------------------------------------------------------------
Agust?n Guti?rrez, PhD
Marie Curie Fellow
Departament d'Electronica
Universitat de Barcelona
Mart? i Franqu?s 1
08028-Barcelona
Phone: +34 93 4039174
Fax: +34 93 4021148
--------------------------------------------------------------------------------
From mark.plumbley at elec.qmul.ac.uk Wed Feb 28 12:40:18 2007
From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley)
Date: Wed, 28 Feb 2007 17:40:18 -0000
Subject: Connectionists: 2nd Call for Papers: ICA 2007 - Intl. Conf. on
Independent Component Analysis and Signal Separation
Message-ID: <3399496864F99445B051FD9556FF3B6F1DACB8@staff-mail1.vpn.elec.qmul.ac.uk>
*** 2nd CALL FOR PAPERS ***
ICA 2007
7th International Conference on
Independent Component Analysis
and Signal Separation
London, UK
9-12 September 2007
www.ica2007.org
The 7th International Conference on Independent Component Analysis and
Signal Separation (ICA 2007) will be held at Queen Mary, University of
London, from Sunday 9 September to Wednesday 12 September 2007.
Independent Component Analysis and Signal Separation is one of the most
exciting current areas of research in statistical signal processing and
unsupervised machine learning. Following the previous ICA conferences in
Aussois (France), Helsinki (Finland), San Diego (CA, USA), Nara (Japan),
Granada (Spain) and Charleston (SC, USA), this year the conference is
organized and sponsored by the ICA Research Network, an EPSRC-funded
network of researchers in over 25 UK institutions.
The Conference will include invited talks as well as oral and poster
presentations of refereed papers and special sessions. It will be
organized in a single track and will be selective.
Papers are solicited in all areas of independent component analysis and
signal separation, including blind source separation (BSS), as well
as semi-blind, non-blind, and model-based signal separation. Topics of
interest include (but not limited to) the following:
* Algorithms and Architectures: non-linear ICA, probabilistic models,
sparse coding, linear & nonlinear models, convolutive & noisy models;
* Theory: optimization, complex methods, time-frequency representations;
* Applications: audio, bio-informatics, biomedical engineering,
communications, finance, image processing, psychology;
* Emerging Technologies: analogue and digital VLSI implementations,
photonics;
* Functional Neuroimaging: EEG, ERP, MEG, fMRI, applications in
neuroscience;
* Speech and Musical Audio: source separation, denoising,
dereverberation, temporal models, computational auditory scene
analysis (CASA), beamforming;
* Visual and Sensory Processing: image processing and coding, image
separation.
All contributions must be original, and must not have been previously
published, nor be under review for presentation elsewhere. Detailed
instructions for submission to ICA?2007, including formatting
instructions and templates, will be available from the conference
website at http://www.ica2007.org
Important Deadlines
Special session proposals: 1 March 2007
Paper submission deadline: 23 March 2007
----------------------------------------------------------------------
Dr Mark D Plumbley
Department of Electronic Engineering
Queen Mary University of London
Mile End Road, London E1 4NS, UK
Tel: +44 (0)20 7882 7518
Fax: +44 (0)20 7882 7997
Email: mark.plumbley at elec.qmul.ac.uk
http://www.elec.qmul.ac.uk/people/markp/