High efficiency learning network

Details High efficiency learning network High efficiency learning network

1993-11-09

1995-12-05

Davis, George B.

395 27, 395 23, G06F 1518, G06K 966

Patent

active

054737303

ABSTRACT:
Nodal outputs are discretized to values of S2.sup.n where n is an integer and S is equal to +1 or -1. During forward propagation, this offers the advantage of forming a product of a nodal output and a weight using a simple shift operation rather than a multiply operation. Replacing multiply operations with shift operations through out a neural network improves response times and permits building larger networks that have broader applicability. Training is also improved by increasing the efficiency of backward propagation. The multiplications involved in backward propagation are reduced To shift operations by discretizing the errors associated with each node so that they are represented as 2.sup.n where n is an integer and S is equal to +1 or -1.

REFERENCES:
patent: 4972363 (1990-11-01), Nguyen et al.
patent: 4994982 (1991-02-01), Duranton et al.
patent: 5058179 (1991-10-01), Denker et al.
patent: 5067164 (1991-11-01), Denker et al.
patent: 5097141 (1992-03-01), Leivian et al.
patent: 5109351 (1992-04-01), Simar, Jr.
patent: 5131072 (1992-07-01), Yoshizawa et al.
patent: 5138924 (1992-08-01), Ohya et al.
patent: 5167006 (1992-11-01), Furuta et al.
patent: 5222195 (1993-06-01), Alkon et al.
patent: 5228113 (1993-07-01), Shelton
patent: 5255346 (1993-10-01), Wu et al.
patent: 5274746 (1993-12-01), Mashiko
patent: 5337395 (1994-08-01), Vassiliadis et al.
Rumelhart et al, "Parallel Distributed Processing" vol. 1, The MIT Press, 1986.
Tank et al, "Simple Neural Optimization Network", IEEE Trans. on Circuit & Systems, May 1986.
Suter et al, "Neural Wet Simulation on Transputers", Royal Melbourne Institute of Tech., Jun. 23-24, 1988.

Affiliated with

Also associated with

Rating

High efficiency learning network does not yet have a rating. At this time, there are no reviews or comments for this patent.

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1380715