AIMS AND SCOPE

 
Incremental Learning is a subfield of the Artificial Intelligence that deals with data flow. The key hypothesis is that the algorithms are able to learn data from a data subset and then to re-learn with new unlabeled data. At the end of the learning, one of the problems is the clustering analysis and visualization of the results. The topological learning is one of the most known technique that allows clustering and visualization simultaneously. At the end of the topographic learning, "similar'' data will be collect in clusters, which correspond to the sets of similar observations. These clusters can be represented by more concise information than the brutal listing of their patterns, such as their gravity center or different statistical moments. As expected, this information is easier to manipulate than the original data points.

Dimensionality reduction is another major challenge in the domain of unsupervised learning which deals with the transformation of a high dimensional dataset into a low dimensional space, while retaining most of the useful structure in the original data, retaining only relevant features and observations. Dimensionality reduction can be achieved by using a clustering technique to reduce the number of observations or a features selection approach to reduce the features space.

This session would solicit theoretical and applicative research papers including but not limited to the following topics :

·Supervised/Unsupervised Topological Learning;
·Self-Organization (based on artificial neural networks, but not limited to);
·Clustering Visualization and Analysis;
·Time during the learning process;
·Memory based systems;
·Online Learning;
·User interaction models;
·Fusion (Consensus) based models;
·Clustering;
·Feature selection;


ORGANIZERS

  • Nistor GROZAVU, Post-Doc, Computer Science Laboratory of Paris 13 University, FRANCE
  • Mustapha LEBBAH, Associate Professor at the Paris 13 University, FRANCE
  • Younès BENNANI, Full Professor at the Paris 13 University, FRANCE


IMORTANT DATES

  • Paper Submission Deadline: 4 April  Extended Deadline : 11 April
  • Notification of acceptance: 22 April
  • Camera-ready papers: 29 April

Submissions

The special session will be held as a part of the ICNNAI'2010 conference (The 5th International Conference on Neural Network and Artificial Intelligence ) . The authors would submit papers through easychair site : http://www.easychair.org/conferences/?conf=itlmdr10.
    
Papers must correspond to the requirements detailed in the instructions to authors from the ICNNAI 2010 web site. Accepted papers must be presented by one of the authors to be published in the conference proceeding.

SUBMISSION REQUIREMENTS
    • The submitted paper has to be substantially new research which has not been published previously.

    • Submission should be no longer than 8 pages.

    • Papers should be submitted by the deadline via Easy-Chair - an automatic submission and review service.

    • By submitting a paper, the authors agree that, if their paper is accepted, they will prepare a camera-ready version in accordance with the changes requested by the reviewers by the deadline for camera-ready papers. They also agree that at least one author will attend the conference and present the paper.

INSTRUCTION FOR AUTHORS

The paper should be followed the Instruction for authors described in the smple.pdf found in the authors' kit which can be downlorded by clicking for LaTeX or for MS-WORD

Contact

If you have any questions, do not hesitate to direct your questions to nistor.grozavu@lipn.univ-paris13.fr

Comments