Topics

The research in the neural network field has come to its maturity, both from the theoretical and the practical point of view. Nevertheless, some problems still remain unsolved, since classical connectionist models seem unable to cope with difficult applications, involving complex data. Recent studies on statistical pattern recognition and neural networks show possible directions to exploit structural information in problems which are inherently of topological nature. On the other hand, the actual trend for facing difficult applications is that of using hybrid approaches, integrating in a unique framework neural networks, kernel machines, and statistical techniques. This new scenario imposes studying new models, new learning algorithms, and assessing their properties both theoretically and experimentally.
The scope of this session is, but not limited to:

• Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, dimensionality reduction and manifold learning, model selection.
• Applications: innovative applications that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics.
• Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, reasoning, problem solving, and natural language processing.
• Control and Reinforcement Learning: planning, navigation, Markov decision processes, game-playing.
• Learning Theory: generalization, regularization and model selection, advanced mathematical methods and new learning paradigms, spaces of functions and kernels, online learning and competitive analysis, hardness of learning and approximations, information theory.
• Learning in Graphical Domains: neural network models for graphs, SVMs and kernel methods for graphs, probabilistic models for graphs, statistical relational learning, and pattern recognition applications involving graphical data.

Paper submission

Authors are encouraged to submit high quality, original work that has neither appeared in, nor is under consideration by, other conferences/journals. All submissions will be refereed by experts in the field based on originality, significance, and clarity. The conference preceedings will be published by Springer-Verlag in Lecture Notes in AI as part of the LNCS/LNAI series. When formatting papers - that must be no more than eight (8) pages long, including figures and bibliography - please refer to the Springer-Verlag site and strictly follow the instructions for LNCS authors (http://www.springer.de/comp/lncs/authors.html).


Important Dates

Chairs

Monica Bianchini, Marco Maggini, Franco Scarselli
Dipartimento di Ingegneria dell'Informazione
University of Siena, Italy
Email:{monica,marco,franco}diiunisiit