System and method for a learning neural network for generating r

Details System and method for a learning neural network for generating r System and method for a learning neural network for generating r

1993-10-04

1995-10-03

Downs, Robert W.

395 27, G06F 1518

Patent

active

054558913

ABSTRACT:
A learning neural network (30) implements a random weight change learning algorithm within a weight adjustment mechanism (28) for manipulating the weights applied to inputs of the network (30) in order to achieve a desired functionality for the network (30). Weights are changed randomly from an initial state with a small incremental weight change of either +.delta. or -.delta.. If the overall network output decreases by the weight change, the same weight change is iterated until the error increases. If, however, the overall network error increases, the weights are changed randomly again. After iterating the foregoing methodology, the network error gradually decreases and finally reaches approximately zero. Furthermore, a shift mechanism (36) and a multiplier (38) are employed as a weight application mechanism (16). The shift mechanisms (36) are connected in series with a random line (35) and are connected in parallel with a shift line (44). A random direction is successively channelled through the shift mechanisms (36) via the random line (35) under the control of the shift line ( 44) so that only a single random number need be generated for all of the shift mechanisms (36) within the neural network (30).

REFERENCES:
patent: 4493046 (1985-01-01), Watanabe
patent: 5168550 (1992-12-01), Sakaue et al.
patent: 5214746 (1993-05-01), Fogel et al.
patent: 5258903 (1993-11-01), Rodriguez-Cavazos
patent: 5324991 (1994-06-01), Furuta et al.
Caudill, M., "Neural Network Training TIPS and Techniques", AI Expert, Jan. 1991, 56-61.
Alspector, et al., "A VLSI-Efficient Technique for Generating Multiple Uncorrelated Noise Sources and Its Application to Stochastic Neural Networks", IEEE Trans. on Circuits and Systems, Jan. 1991, 109-123.
Cho, et al., "Fast Back-Propagation Learning Using Steep Activation Functions and Automatic Weight Reinitialization", Proc. 1991 IEEE Int'l. Conf. on Syst., Man., and Cybernetics, Oct. 1991, 1587-1592.
Von Lehmen, et al., "Factors Influencing Learning by Back-Propagation", IEEE Int'l. Conf. on Neural Networks, Jul. 1988, I-335-I-341.
McClelland, et al., Explorations in Parallel Distributed Processing, MIT Press, 1988, 137-141.
Narendra, et al., "Identification and Control of Dynamical Systems Using Neural Networks", IEEE Trans. on Neural Networks, Mar. 1990, 4-26.
Schwartz, T., "A Neural Chips Survey", AI Expert, Dec. 1990, 34-39.

Affiliated with

Also associated with

Rating

System and method for a learning neural network for generating r does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System and method for a learning neural network for generating r, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for a learning neural network for generating r will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1082626