Connectionists: ESANN'18 SS 1st CPF - SHALLOW and DEEP MODELS for TRANSFER LEARNING and DOMAIN ADAPTATION

[Siamak Mehrkanoon]

*** Apologies if you receive multiple copies of this CFP ***

CALL FOR PAPERS:
special session on "SHALLOW and DEEP MODELS for TRANSFER LEARNING and
DOMAIN ADAPTATION" at ESANN 2018

European Symposium on Artificial Neural Networks, Computational
Intelligence and Machine Learning (ESANN 2018). 25-27 April 2018, Bruges,
Belgium
http://www.esann.org

____________
DESCRIPTION:
Manual labeling of sufficient training data for diverse application domains
is a costly, laborious task and often prohibitive. Therefore, designing
models that can leverage rich labeled data in one domain and be applicable
to a different but related domain is highly desirable. In particular,
domain adaptation or transfer learning algorithms seek to generalize a
model trained in a source domain (training data) to a new target domain
(test data). The most common underlying assumption of many machine learning
models is that both training and test data exhibit the same distribution or
the same feature domains. However, in many real life problems, there is a
distributional, feature space and/or dimension mismatch between the two
domains or the statistical properties of the data evolve in time.
Transferring and incorporating different sources of information such as
learned feature extractors, knowledge of labeled and unlabeled instances,
learned parameters among others from different domains into a unified model
that can leverage all the available prior knowledge in order to achieve
human level accuracy on a given new task is of great importance. In this
context, depending on the availability of the labeled and unlabeled
training data from (i) source domains, (ii) source and target domains,
different scenarios related to supervised as well as semi-supervised domain
adaptation can for instance be considered. In addition different modeling
strategies ranging from shallow to deep models is of interest.

Therefore, the main objective of the session is to discuss the recent rise
of new research questions and learning strategies for the domain adaptation
and transfer learning problems using
both shallow and deep models. The goal is to promote a fruitful exchange of
ideas and methods between different communities, leading to a global
advancement of the field.

Topics for submission include but are not limited to:

          • Deep and shallow models
          • Neural Networks
          • Kernel based models
          • Transfer learning and domain adaptation
          • Feature learning / representation learning
          • Domain invariant features
          • Supervised / Semi-supervised Learning
          • Fine-tuning / Feature extractor / Amount of labeling
          • Scalability
          • Regularization

___________
SUBMISSION:
Submitted papers must follow the ESANN paper format and guidelines.
https://www.elen.ucl.ac.be/esann/index.php?pg=submission .
Authors are encouraged to send as soon as possible an e-mail with the
tentative title of their contributions to the special session organisers.

___________________
PRELIMINARY DATES:
Full Paper submission:  20 November 2017
Notification of acceptance:  31 January 2018

_____________________________
SPECIAL SESSION ORGANISERS:

• Siamak Mehrkanoon
  ESAT-STADIUS, KU Leuven, Belgium
  E-mail: Siamak.Mehrkanoon at esat.kuleuven.be
  Website: http://mehrkanoon2011.wixsite.com/siamak-mehrkanoon

• Matthew Blaschko
  ESAT-PSI, KU Leuven, Belgium
  E-mail: Matthew.Blaschko at esat.kuleuven.be
  Website: http://homes.esat.kuleuven.be/~mblaschk/

• Johan A.K. Suykens
  ESAT-STADIUS, KU Leuven, Belgium
  E-mail: Johan.Suykens at esat.kuleuven.be
  Website: http://www.esat.kuleuven.be/sista/members/suykens.html
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20170903/553e5652/attachment.html>