Technical Report Series in Neural and Computational Learning (second attempt to send)

Fri Jun 19 16:01:26 EDT 1998

[Apologies if you get more than one copy: the first attempt ]
[had some non-deliveries.            rgds, K.               ]

The European Community ESPRIT Working Group in Neural and Computational
Learning Theory (NeuroCOLT) has been funded for a further three years
as the Working Group NeuroCOLT2. The overall objective of the Working
Group is to demonstrate the effectiveness of technologies that arise
from a deep understanding of the performance and implementation of
learning systems on real world data. We will continue to maintain the
Technical Report Archive of papers produced by members or associates of
the group's partners. We have created a new web site:
	http://www.neurocolt.com/ 
which gives more information about the project, including access to the
Technical Reports (see below for further access instructions).

Best wishes
John Shawe-Taylor

--------------------------------------------------------------------

Titles follow:
Abstracts are available via the Web Site

1998 Document Archive

    Ref.                    Title                        Author         

  1998-abs                Complete Abstract File For 1998              

            JNN, a Randomized Algorithm for                            
  1998-001  Learning Multilayer Networks in       Elisseeff &
            Polynomial Time                       Paugam-Moisy         

  1998-002  A comparison of non-informative       Grunwald
            priors for Bayesian networks                               

            Data-Dependent Structural Risk                             
  1998-003  Minimisation for Perceptron Decision  Shawe-Taylor
            Trees                                                      

  1998-004  Are Lower Bounds Easier over the      Fournier & Koiran
            Reals?                                                     

  1998-005  Query, PACS and simple-PAC Learning   Castro & Guijarro

  1998-006  The Real Dimension Problem is         Koiran
            NPR-Complete                                               

  1998-007  Elimination of Parameters in the      Koiran
            Polynomial Hierarchy                                       

            Bayesian Classifiers are Large        Cristiani,           
  1998-008  Margin Hyperplanes in a Hilbert       Shawe-Taylor,
            Space                                 Sykacek              

  1998-009  Learning via Internal Representation  Dichterman

            Discrete versus analog computation:

  1998-010  Some aspects of studying the same     Meer
            problem in different computational                         
            models

  1998-011  How many connected components must a  Matamala & Meer
            difficult set have?                                        

            The Separation Theorem for the                             
  1998-012  Relation Classes Associated to the    Gakwaya
            Extended Grzegorczyk Classes                               

            Isomorphism Theorem for BSS                                
  1998-013  Recursively Enumerable Sets over      Michaux & Troestler
            Real Closed Fields                                         

            Efficient Read-Restricted Monotone                         
  1998-014  CNF/DNF Dualization by Learning with  Domingo, Mishra,
            Membership Queries                    Pitt                 

  1998-015  Equality Is a Jump                    Boldi & Vigna

                                                  Cristianini,         
  1998-016  Multiplicative Updatings for          Campbell,
            Support-Vector Learning                                    
                                                  Shawe-Taylor

                                                  Cristianini,         
  1998-017  Dynamically Adapting Kernels in       Campbell,
            Support Vector Machines                                    
                                                  Shawe-Taylor

  1998-018  Practical Algorithms for On-line      Domingo, Gavalda,
            Sampling                              Watanabe             

---------------------------------------------------------------------------

***************** ACCESS INSTRUCTIONS ******************

The files and abstracts may be accessed via WWW starting from the NeuroCOLT 
homepage:

http://www.neurocolt.com/

or from the archive:
ftp://ftp.dcs.rhbnc.ac.uk/pub/neurocolt/tech_reports

Alternatively, it is still possible to use ftp access as follows:

% ftp ftp.dcs.rhbnc.ac.uk  (134.219.96.1)
Name: anonymous
password: your full email address
ftp> cd pub/neurocolt/tech_reports/1998
ftp> binary
ftp> get nc-tr-1998-001.ps.Z
ftp> bye
% zcat nc-tr-1998-001.ps.Z | lpr 

Similarly for the other technical reports.

In some cases there are two files available, for example,
nc-tr-97-002-title.ps.Z
nc-tr-97-002-body.ps.Z
The first contains the title page while the second contains the body 
of the report. The single command,
ftp> mget nc-tr-97-002*
will prompt you for the files you require.

---------------------------------------------------------------------
| Keith Howker                     |   e-mail: jkh at dcs.rhbnc.ac.uk  |
| Dept. of Computer Science        |   Phone : +44 1784 443696      |
| RHUL                             |   Fax   : +44 1784 439786      |
| EGHAM  TW20  0EX, UK             |   Home:   +44 1932 222529      |
---------------------------------------------------------------------

---------------------------------------------------------------------
| Keith Howker                     |   e-mail: jkh at dcs.rhbnc.ac.uk  |
| Dept. of Computer Science        |   Phone : +44 1784 443696      |
| RHUL                             |   Fax   : +44 1784 439786      |
| EGHAM  TW20  0EX, UK             |   Home:   +44 1932 222529      |
---------------------------------------------------------------------