A neural network model for temporal sequence learning and motor programming

Abstraet-A neural network model for fast learning and storage of temporal sequences is presented. The recall of a learned sequence is triggered by the occurrence of an item relating to its identity, and one of the main distinctive features of this model is that the speed at which a sequence is repeated can be freely modulated by a control subsystem. The possible applications of the model are illustrated by applying it to the production of motor forms. It is shown that any spatial shape memorized in exteroceptive terms can be reproduced in terms of movement by any of the effector systems of the body, and in particular by a simulated jointed arm, at any point in its working space and at any suitable size scale. Our theoretical approach reinforces the idea that the structures responsible for planning a movement in the central nervous system might be largely independent of the motor systems performing this movement.

[1]  J. Hérault,et al.  Réseau de neurones à synapses modifiables: décodage de messages sensoriels composites par apprentissage non supervisé et permanent , 1984 .

[2]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[3]  B. Ans,et al.  Simulation de réseaux neuronaux (SIRENE). I: Le modèle , 1983 .

[4]  Geoffrey E. Hinton,et al.  Lesioning an attractor network: investigations of acquired dyslexia. , 1991, Psychological review.

[5]  S Dehaene,et al.  Neural networks that learn temporal sequences by selection. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[7]  J. Changeux,et al.  The Wisconsin Card Sorting Test: theoretical analysis and modeling in a neuronal network. , 1991, Cerebral cortex.

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  S. Grossberg.  Contour Enhancement , Short Term Memory , and Constancies in Reverberating Neural Networks , 1973 .

[10]  Shik Ml,et al.  Control of walking and running by means of electric stimulation of the midbrain , 1966 .

[11]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[12]  Stephen Grossberg.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987 .

[13]  John G. Taylor,et al.  Storing temporal sequences , 1991, Neural Networks.

[14]  Teuvo Kohonen,et al.  Associative memory. A system-theoretical approach , 1977 .

[15]  B Ans.  [Associative learning in a neuromimetic network with local competitions]. , 1990, Comptes rendus de l'Academie des sciences. Serie III, Sciences de la vie.

[16]  Francis Crick,et al.  The recent excitement about neural networks , 1989, Nature.

[17]  M. L. Shik,et al.  [Control of walking and running by means of electric stimulation of the midbrain]. , 1966, Biofizika.

[18]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[19]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[20]  M. Konishi,et al.  Birdsong: from behavior to neuron. , 1985, Annual review of neuroscience.

[21]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[22]  Pei-chun P. Liu,et al.  Associative memory system , 1994 .

[23]  N. A. Bernshteĭn.  The co-ordination and regulation of movements , 1967 .

[24]  P. Viviani,et al.  32 Space-Time Invariance in Learned Motor Skills , 1980 .

[25]  J. Changeux,et al.  A Simple Model of Prefrontal Cortex Function in Delayed-Response Tasks , 1989, Journal of Cognitive Neuroscience.

[26]  P. Matthews,et al.  Mammalian muscle receptors and their central actions , 1974 .

[27]  B. Ans,et al.  Simulation de réseaux neuronaux (SIRENE). II: Hypothése de décodage du message de mouvement porté par les afférences fusoriales IA et II par un mécanisme de plasticité synaptique , 1983 .

[28]  G. W. Strong,et al.  A solution to the tag-assignment problem for neural networks , 1989, Behavioral and Brain Sciences.

[29]  B Ans.  [Neuromimetic model for storage and recall of temporal sequences]. , 1990, Comptes rendus de l'Academie des sciences. Serie III, Sciences de la vie.

[30]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..