Multi-layer network and learning method therefor

Details Multi-layer network and learning method therefor Multi-layer network and learning method therefor

1990-12-10

1993-05-18

MacDonald, Allen R.

395 11, 395800, G06F 1518

Patent

active

052127672

ABSTRACT:
A multi-layer neural network comprising an input layer, a hidden layer and an output layer and a learning method for such a network are disclosed. A processor belonging to the hidden layer stores both the factors of multiplication or weights of link for a successive layer nearer to the input layer and the factors of multiplication or weights of link for a preceding layer nearer to the output layer. Namely, the weight for a certain connection is doubly stored in processors which are at opposite ends of that connection. Upon forward calculation, the access to the weights for the successive layer among the weights stored in the processors of the hidden layer can be made by the processors independently from each other. Similarly, upon backward calculation, the access to weights for the preceding layer can be made by the processors independently from each other.

REFERENCES:
patent: 4941122 (1990-07-01), Weideman
patent: 4947482 (1990-08-01), Brown
patent: 4974169 (1990-11-01), Engel
patent: 4994982 (1991-02-01), Duranton et al.
patent: 5040230 (1991-08-01), Takatori et al.
patent: 5046019 (1991-09-01), Basehore
Eberhardt et al., "Design of Parallel Hardware Neural Network Systems from Custom Analog VLSI `Building Block` Chips", Internat. Joint Conf. on Neural Networks 1989, vol. 2, pp. 183-190, Jun. 18-22, 1989.
Yasunaga et al., "A Water Scale Integration Neural Network Utilizing Completely Digital Circuits", Internat. Joint Conf. on Neural Networks, Jun. 18-22, 1989, vol. 2, pp. 213-217.
Lippmann, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
Yukimasa Sato, et al., "A Neural Network Accelerator Using General Purpose Floating Point Digital Signal Processors", Technical & Research Report of the Institute of Electronics, Information and Communication Engineers of Japan, ME and Biocybernetics 88-134, 1989, pp. 83-88. (English translation unavailable).
D. E. Rumelhart, et al., Chap. 8 "Learning Internal Representations by Error Propagation", Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations, The MIT Press, Cambridge, Mass. (1986), pp. 318-362. (Provided in English).

Affiliated with

Also associated with

Rating

Multi-layer network and learning method therefor does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Multi-layer network and learning method therefor, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multi-layer network and learning method therefor will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-809697