Neural network and method for operating the same

Details Neural network and method for operating the same Neural network and method for operating the same

1995-11-20

1997-05-27

Downs, Robert W.

G06F 1500, G06F 1518

Patent

active

056340630

ABSTRACT:
A neural network provides faster learning speed and simplified overall structure through use of the concept of indirect association and a method for operating the same. The neural network is constructed as a CLCAM comprising an input-side single layer perceptron adapted to realize direct associations (X.sub.i,Z.sub.1i) as linearly separable problems with respect to given inputs (X.sub.i) and first intermediate states (Z.sub.1i) derived by the user, an output-side single layer perceptron adapted to realize direct associations (Z.sub.2i,Y.sub.i) as linearly separable problems with respect to given outputs (Y.sub.i) and second intermediate states (Z.sub.2i) derived by the user, and a location addressable memory adapted to connect said first intermediate states (Z.sub.1i) with said second intermediate states (Z.sub.2i). The neural network is also constructed as HyLCAM comprising a single layer perceptron adapted to realize direct associations (X.sub.i,Z.sub.i) as linearly separable problems with respect to given inputs (X.sub.i) and intermediate states (Z.sub.i) manually derived by the user, and a location addressable memory adapted to receive the intermediate states (Z.sub.i) from the single layer perceptron as addresses and store given output data (Y.sub.i) as desired output values, correspondingly to the addresses.

REFERENCES:
patent: 4897811 (1990-01-01), Scofield
patent: 4995088 (1991-02-01), Farhat
patent: 5023833 (1991-06-01), Baum et al.
patent: 5107454 (1992-04-01), Niki
patent: 5220559 (1993-06-01), Tsuzuki et al.
patent: 5222195 (1993-06-01), Alkon et al.
patent: 5253328 (1993-10-01), Hartman
patent: 5459817 (1995-10-01), Shima
D.E. Rumelhart et al., "Learning Internal Representations by Error Propagation", Cambridge, MA, MIT Press, 1988, pp. 318-362.
K. Hornik et al., "Multilayer Feed Forward Networks are Universal Approximators", Neural Networks, vol. 2, No. 5, pp. 359-366, 1989.
Hartman, Dec. 31, 1991, A High Storage Capacity Neural Net Content-Addressable Memory, Network 2, Neural Net. Arch. for CAM.
Tarassenko et al., IEEE, Feb. 1991, VLSI, "Implementation of a Neural Associative Memory and Its Application to Vector Quantization".
Goodman et al., Jul. 9, 1990, International Neural Network Conference, Jul. 9-13, 1990.
Wang et al., "Hybrid Location-Content Addressable Memory", IEEE, Mar. 28 Apr., 1, 1993.

Affiliated with

Also associated with

Rating

Neural network and method for operating the same does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network and method for operating the same, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network and method for operating the same will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2336361