Neutral network with plural weight calculation methods and varia

Details Neutral network with plural weight calculation methods and varia Neutral network with plural weight calculation methods and varia

1990-02-20

1992-12-01

MacDonald, Allen R.

G06F 1518

Patent

active

051685507

ABSTRACT:
An iterative learning machine uses, as a direction of changing iterative weight, a conjugate gradient direction in place of the conventional steepest descent direction, thereby saving time. Learning rates are set dynamically. Error calculation for plural learning rates, with respect to a certain weight changing direction, are accomplished by storing a product-sum of the input signals and weights in a hidden layer and a product-sum of the input signals and the weight changing direction in the hidden layer. When the learning falls into a non-effective state where further iteration does not effectively reduce an error, the weights are adjusted in order to restart the learning.

REFERENCES:
Improving the Learning Rate of Back-Propagation with the Gradient Reuse Algorithm; Hush et al; IEEE Inter. Conf. on Neutral Networks; Jul. 24-27, 1988; pp. I-441 to I-446.
Learning Internal Representations by Error Propagation; Rumelhart et al.; Parallel Distributed Processing, vol. 1, Foundations; MIT Press; 1986; pp. 318-362.
"Learning representations by back-propagating errors", David Rumelhart et al.; Nature, vol. 323, Oct. 1986, pp. 533-536.
DUTTA, "Bond Ratings: A non-conservative application of neutral networks", IEEE International Conference on Neutral Networks, vol. 2, pp. 443-450, Jul. 24, 1988.
Watrous, "Learning algorithms for connectionist networks: applied gradient methods of nonlinear optimization", IEEE First National Conference on Neutral Networks, vol. 2, pp. 619-628, Jun. 21, 1987.
JACOBS, "Increased rates of convergence through learning rate adaption", Neutral Networks, vol. 1, No. 4, pp. 295-307, 1988.

Affiliated with

Also associated with

Rating

Neutral network with plural weight calculation methods and varia does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neutral network with plural weight calculation methods and varia, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neutral network with plural weight calculation methods and varia will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-508113