LEAD

Robert FRENCH

Directeur de Recherche CNRS, LEAD UMR 5022
Université de Bourgogne

« Un modèle connexionniste de chunking et de segmentation : Un défi relevé et remporté »

Individuals of all ages extract structure from the sequences of patterns they encounter in their environment, an ability that is at
the very heart of cognition. Exactly what underlies this ability has been the subject of much debate over the years. A novel mechanism, implicit chunk recognition (ICR), is proposed for sequence segmentation and chunk extraction. The mechanism relies on the recognition of previously encountered subsequences (chunks) in the input rather than on the prediction of upcoming items in the input sequence. A connectionist autoassociator model of ICR, truncated recursive autoassociative chunk extractor (TRACX), is presented in which chunks are extracted by means of truncated recursion. The performance and robustness of the model will be illustrated by comparing the results of the model to empirical data from infant statistical learning and adult implicit learning. I will also present a simulation demonstrating the model's ability to generalize to new input and to develop internal representations whose structure reflects that of the items in the input sequence. Our results suggest that TRACX outperforms its main computational competitors, PARSER (Perruchet & Vintner, 1998) and the simple recurrent network (SRN, Cleeremans & McClelland, 1991), in matching human sequence segmentation on existing data.