Of points and loops

New learning rules for the storage and retrieval of temporal sequences, in neural networks with parallel synchronous dynamics, are presented. They allow either one-shot, non-local learning, or slow, local learning. Sequences with bifurcation points, i.e. sequences in which a given state appears twice, or in which a given state belongs to two distinct sequences, can be stored without errors and retrieved.

[1]  D Kleinfeld,et al.  Sequential state generation by model neural networks. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Kanter,et al.  Temporal association in asymmetric neural networks. , 1986, Physical review letters.

[3]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Opper,et al.  Learning of correlated patterns in spin-glass networks by local learning rules. , 1987, Physical review letters.

[5]  A. A. Mullin,et al.  Principles of neurodynamics , 1962 .

[6]  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.

[7]  Kanter,et al.  Associative recall of memory without errors. , 1987, Physical review. A, General physics.

[8]  Hermann Haken,et al.  Computational Systems - Natural and Artificial , 1987 .

[9]  I. Guyon,et al.  Information storage and retrieval in spin-glass like neural networks , 1985 .

[10]  L. Personnaz,et al.  Collective computational properties of neural networks: New learning mechanisms. , 1986, Physical review. A, General physics.