HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Molter, C. Articles by Bersini, H. Search for Related Content PubMed Articles by Molter, C. Articles by Bersini, H.

The Road to Chaos by Time-Asymmetric Hebbian Learning in Recurrent Neural Networks

cmolter{at}brain.riken.jp Laboratory for Dynamics of Emergent Intelligence, RIKEN Brain Science Institute, Wako, Saitama, 351-0198, Japan, and Laboratory of Artificial Intelligence, IRIDIA, Université Libre de Bruxelles, 1050 Brussels, Belgium

Utku Salihoglu

usalihog{at}ulb.ac.be Laboratory of Artificial Intelligence, IRIDIA, Université Libre de Bruxelles, 1050 Brussels, Belgium

Hugues Bersini

bersini{at}ulb.ac.be Laboratory of Artificial Intelligence, IRIDIA, Université Libre de Bruxelles, 1050 Brussels, Belgium

This letter aims at studying the impact of iterative Hebbian learning algorithms on the recurrent neural network's underlying dynamics. First, an iterative supervised learning algorithm is discussed. An essential improvement of this algorithm consists of indexing the attractor information items by means of external stimuli rather than by using only initial conditions, as Hopfield originally proposed. Modifying the stimuli mainly results in a change of the entire internal dynamics, leading to an enlargement of the set of attractors and potential memory bags. The impact of the learning on the network's dynamics is the following: the more information to be stored as limit cycle attractors of the neural network, the more chaos prevails as the background dynamical regime of the network. In fact, the background chaos spreads widely and adopts a very unstructured shape similar to white noise.

Next, we introduce a new form of supervised learning that is more plausible from a biological point of view: the network has to learn to react to an external stimulus by cycling through a sequence that is no longer specified a priori. Based on its spontaneous dynamics, the network decides "on its own" the dynamical patterns to be associated with the stimuli. Compared with classical supervised learning, huge enhancements in storing capacity and computational cost have been observed. Moreover, this new form of supervised learning, by being more "respectful" of the network intrinsic dynamics, maintains much more structure in the obtained chaos. It is still possible to observe the traces of the learned attractors in the chaotic regime. This complex but still very informative regime is referred to as "frustrated chaos."