Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A short-term neural network memory

Journal Article · · SIAM J. Comput.; (United States)
DOI:https://doi.org/10.1137/0217071· OSTI ID:6347350

Neural network memories with storage prescriptions based on Hebb's rule are known to collapse as more words are stored. By requiring that the most recently stored word be remembered precisely, a new simple short-term neutral network memory is obtained and its steady state capacity analyzed and simulated. Comparisons are drawn with Hopfield's method, the delta method of Widrow and Hoff, and the revised marginalist model of Mezard, Nadal, and Toulouse.

Research Organization:
AT and T Bell Labs., Holmdel, NJ (US)
OSTI ID:
6347350
Journal Information:
SIAM J. Comput.; (United States), Journal Name: SIAM J. Comput.; (United States) Vol. 17:6; ISSN SMJCA
Country of Publication:
United States
Language:
English

Similar Records

A high-storage capacity content-addressable memory and its learning algorithm
Journal Article · Mon May 01 00:00:00 EDT 1989 · IEEE (Institute of Electrical and Electronics Engineers) Transactions on Circuits and Systems; (USA) · OSTI ID:5172980

Associative memory in phasing neuron networks
Conference · Thu May 01 00:00:00 EDT 2014 · OSTI ID:1156778

Adiabatic quantum optimization for associative memory recall
Journal Article · Sun Dec 21 23:00:00 EST 2014 · Frontiers in Physics · OSTI ID:1185587