Patent
1993-07-02
1996-06-04
Downs, Robert W.
395 22, G06F 1518
Patent
active
055241778
ABSTRACT:
The learning of an associative memory suitable for the connectionist model which can deal with the patterns having the non-random frequencies of the appearances or the non-random correlations. In this invention, the learning of the associative memory in a form of a neural network, in which a plurality of nodes having activation values are connected by a plurality of links having link weight values, is achieved by entering a plurality of learning patterns sequentially, where each learning pattern has a plurality of elements in correspondence with the nodes, calculating an energy E of the entered learning pattern, determining a learning amount .delta. for the entered learning pattern according to a difference between the calculated energy E and a predetermined reference energy level Eth, and updating the link weight values of the links according to the entered learning pattern and the determined learning amount .delta..
REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4874963 (1989-10-01), Alspector
patent: 5050095 (1991-09-01), Samad
patent: 5086479 (1992-02-01), Takenaga et al.
patent: 5150450 (1992-09-01), Swenson et al.
patent: 5253328 (1993-10-01), Hartman
patent: 5257343 (1993-10-01), Kyuma et al.
Collins, "A Neural Network Based on Co-Occurrence Probabilities", IEEE 1st Int'l Conf on Neural Networks, pp. 487-494, Jun. 21-24 1987.
Kosko, "Bidirectional Associative Memories", IEEE Transactions on Systems, Man & Cybernetics, vol. 18 No. 1 pp. 49-60, Jan. 1988.
Yin et al, "An Associative Memory Model of Language" Int'l Joint Conf. on Nueral Networks, Jun. 17-21 1990, vol. 3 pp. 663-670.
D. E. Rumelhart et al., "Learning Internal Representations by Error Propagation", Parallel Distributed Processing, vol. 1, Chapt. 8, (1986), pp. 318-362.
J. P. Cater, "Successfully Using Peak Learning Rates of 10 (and greater) in Back-propagation Networks with the Heuristic Learning Algorithm", IEEE First Int'l. Conf. on Neural Networks (Jun. 1987), pp. II-645 to II-651.
R. A. Jacobs, "Increased Rates of Convergeence Through Learning Rate Adaptation", Neural Networks (1988), pp. 295-307.
J. L. McClelland and D. E. Rumelhart, Explorations in Parallel Distributed Processing, MIT Press (1988), pp. 137-141.
R. Pedone and D. Parisi, "Learning the learning parameters", IEEE Int'l. Joint Conf. on Neural Networks (Nov. 1991), PP. 2033-2037.
Proceedings of the National Academy of Sciences 79:2554-2558, 1982, J. J. Hopfield, "Neural Networks And Physical Systems With Emergent Collective Computational Abilities".
Cognitive Science, vol. 9, 1985, pp. 51-74, D. L. Waltz, et al., "Massively Parallel Parsing: A Strongly Interactive Model Of Natural Language Interpretation".
Biological Cybernetics, 26, Springer-Verlag 1977, pp. 175-185, S.-I. Amari, "Neural Theory Of Association And Concept-Formation".
Neural Networks, vol. 2, 1989, pp. 451-457, Shun-ichi Amarai, "Characteristics Of Sparcely Encoded Associative Memory".
Europhysics Letters, 10 (7), Dec. 1989, pp. 627-631, C. J. Perez-Vincente, "Finite-Size Capacity Of Sparse-Coding Models".
Downs Robert W.
Kabushiki Kaisha Toshiba
LandOfFree
Learning of associative memory in form of neural network suitabl does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Learning of associative memory in form of neural network suitabl, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning of associative memory in form of neural network suitabl will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-391451