Learning process system for use with a neural network structure

Details Learning process system for use with a neural network structure Learning process system for use with a neural network structure

1993-01-11

1994-07-26

MacDonald, Allen R.

G06F 1518, G06G 760

Patent

active

053332393

ABSTRACT:
A learning process system is provided for a neural network. The neural network is a layered network comprising an input layer, an intermediate layer and an output layer formed of basic units. In the basic units, a plurality of inputs is multiplied by a weight signal and the products are accumulated, thereby supplying the sum of products. An output signal is obtained using a threshold value function in response to the sum of products. An error signal is generated by an error circuit in response to a difference between the output signal obtained from the output layer and a teacher signal. A weight updating signal is determined in a weight learning circuit by obtaining a weight value in which the sum of the error values falls within an allowable range. Thus, the learning is performed in the layered neural network through use of a back propagation method. Through such learning in the layered neural network, an updating quantity to be obtained in the present weight updating cycle is determined in response to a once delayed weight updating quantity signal in a previous weight updating cycle and a twice delayed weight updating quantity obtained at a twice-previous weight updating cycle prior to the previous weight updating cycle.

REFERENCES:
patent: 4807168 (1989-02-01), Moopenn et al.
patent: 4809223 (1989-02-01), Brown
patent: 4858177 (1989-08-01), Smith
patent: 4866645 (1989-09-01), Lish
patent: 4912653 (1990-03-01), Wood
patent: 4912655 (1990-03-01), Wood
patent: 4941122 (1990-07-01), Weideman
patent: 4979126 (1990-12-01), Pao et al.
patent: 4988891 (1991-01-01), Mashiko
patent: 4994982 (1991-02-01), Duranton et al.
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5056037 (1991-10-01), Eberhardt
McClelland et al., Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises, MIT Press, 1988, pp. 2, 3, 137-145.
Raffel et al., "A Generic Architecture for Wafer-Scale Neuromorphic Systems", from Proc. of the IEEE 1st Annual Intl. Conf. on Neural Networks, 1988, vol. II pp. 173-180.
Denning, E., "Accelerated Learning Using the Generalized Delta Rule", IEEE First Intl. Conf. Neural Networks, 1987, I523-530.
Hush et al., "Improving the Learning Rate of Back-Propagation with the Gradient Reuse Algorithm", IEEE Intl. Conf. on Neural Networks, Jul. 1988, I-441-I446.
IEEE International Conference on Neural Networks, San Diego, Calif. 24th-27th Jul. 1988, pp. I-625-I-632; A. Khotanzad et al.: "Distortion invariant character recognition by a multi-layer perceptron and back-propagation learning".
D. E. Rumelhart et al.: "Parallel distributed processing, vol. 1", vol. 1: Foundations:, 1986, pp. 318-362, The MIT Press, U.S.
IEEE International Conference on Neural Networks, San Diego, Calif., 24th-27th Jul. 1988, pp. I-335-I-341; A. Von Lehmen et al.: "Factors influencing learning by backpropagation".

Affiliated with

Also associated with

Rating

Learning process system for use with a neural network structure 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 process system for use with a neural network structure , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning process system for use with a neural network structure will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1057193