Accelerated training apparatus for back propagation networks

Details Accelerated training apparatus for back propagation networks Accelerated training apparatus for back propagation networks

1991-06-17

1993-07-13

MacDonald, Allen R.

G06F 1518

Patent

active

052281132

ABSTRACT:
A supervised procedure for obtaining weight values for back-propagation neural networks is described. The method according to the invention performs a sequence of partial optimizations in order to determine values for the network connection weights. The partial optimization depends on a constrained representation of hidden weights derived from a singular value decomposition of the input space as well as an Iterative Least Squares optimization solution for the output weights.

REFERENCES:
patent: 4933872 (1990-06-01), Vanderberg et al.
patent: 4979126 (1990-12-01), Pao et al.
Rummelhart et al, "Learning Internal Representations by Error Propagation," Parallel Distributed Processing, vol. I, Foundations, Rummelhart and McClelland, eds, pp. 318-362 (1986).
Anton, Elementary Linear Algebra, Third Edition, 1981, pp. 4, 129, 186-187.

Affiliated with

Also associated with

Rating

Accelerated training apparatus for back propagation networks does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Accelerated training apparatus for back propagation networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Accelerated training apparatus for back propagation networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2319044