Patent
1992-12-10
1997-05-27
Davis, George B.
395 20, G06F 716, G06F 1518
Patent
active
056339887
ABSTRACT:
An adaptation method for a data processing system comprising a plurality of neurons each of which outputs an output according to a comparison between a sum of multiplied inputs by weights and a threshold, characterized in the threshold of the neuron which has generated significant output at certain point of time is compulsorily increased to a maximal value and the weight of the neuron is adapted for a constant value of the inputs wherein the threshold is decreased to a value at the point.
REFERENCES:
patent: 3310784 (1967-03-01), Hilinski
patent: 3602731 (1971-08-01), Yanai
patent: 3638196 (1972-01-01), Nishiyama
patent: 3979602 (1976-09-01), Reible
patent: 4535785 (1985-08-01), VandenHonert et al.
patent: 4912655 (1990-03-01), Wood
patent: 4988891 (1991-01-01), Mashiko
patent: 5040230 (1991-08-01), Takatori et al.
VLSI Architectures for Neural Networks, Treleaven et al., IEEE Micro, 1989.
Neural Computing-Theory and Practice, Philip D. Wasserman, 1989.
An Introduction to Computing With Neural Nets, Richard P. Lippmann, IEEE Assp Mag., Apr. 1987.
Neural `selective` Processing and Learning, Patrice Gelb and Edison Tse, IEEE Inter. Conf. on Neural Networks, Jul. 1988, pp. I-417 to I-424.
"VLSI Architectures for Neural Networks", Treleaven et al, IEEE Micro, 1989 .
Kumagai Ryohei
Matsumoto Koji
Takatori Sunao
Yamamoto Makoto
Davis George B.
Yozan Inc.
LandOfFree
Adaptation method for data processing system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Adaptation method for data processing system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptation method for data processing system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2335254