1994-05-13
1998-07-07
Hafiz, Tariq R.
395 21, 395 20, 395 24, G06E 100, G06E 300
Patent
active
057781524
ABSTRACT:
A neural network designed to recognize a particular character is supplied with initial tap weights for a first hidden node which are an image of the character to be recognized. The additive inverse of this set of weights is used as the tap weights for a second hidden node. A third node, if used, is initialized with random noise. The network is then trained with back propagation.
REFERENCES:
patent: 5546503 (1996-08-01), Abe et al.
Khotanzad et al, "Distortion invariant character recognition by a multi-layer perceptron and back-propagation learning"; IEEE International conference on neural networks, pp. 625-632 vol. 1, 24-27, Jul. 1988.
Oki Toru
Paolella Philip A.
Hafiz Tariq R.
Miller Jerry A.
Rode, Esq. Lise A.
Sony Corporation
Sony Electonics Inc.
LandOfFree
Training method for neural 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 Training method for neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training method for neural network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1215901