Digital neural network with discrete point rule space

Details Digital neural network with discrete point rule space Digital neural network with discrete point rule space

1989-10-03

1991-10-15

MacDonald, Allen R.

Boots, shoes, and leggings

G06F 1518

Patent

active

050580345

ABSTRACT:
This application discloses a system that optimizes a neural network by generating all of the discrete weights for a given neural node by creating a normalized weight vector for each possible weight combination. The normalized vectors for each node define the weight space for that node. This complete set of weight vectors for each node is searched using a direct search method during the learning phase to optimize the network. The search evaluates a node cost function to determine a base point from which a pattern more within the weight space is made. Around the pattern mode point exploratory moves are made which are cost function evaluated. The pattern move is performed by eliminating from the search vectors with lower commonality.

REFERENCES:
Implementing Neural Nets with Programmable Logic; J. J. Vidal; IEEE Transactions on Acoustics, Speech, and Signal Processing; vol. 36, No. 7, Jul. 1987; pp. 1180-1190.
Richard O. Duda, Peter E. Hart and Nils J. Nilsson, "Subjective Bayesian methods for rule-based inference systems", pp. 192-199.

Affiliated with

Also associated with

Rating

Digital neural network with discrete point rule space does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Digital neural network with discrete point rule space, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Digital neural network with discrete point rule space will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-995953