CFP: ICNNAI-2010 Special Session: Incremental Topological Learning Models and Dimensional Reduction
Submissions Due: April 4, 2010
1 - 4 June, 2010
Brest State Technical University
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;
· User interaction models;
· Fusion (Consensus) based models;
· Feature selection;
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.
All paper submissions will be handled electronically. Detailed instructions for submitting the papers are provided on the conference home page at :
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. If you have any questions, do not hesitate to direct your questions to email@example.com
Deadline: 4 April
Notification of acceptance: 22 April
Camera-ready papers: 29 April