1994-09-16
1996-11-05
Davis, George B.
395 22, 395 20, G06K 962
Patent
active
055726283
ABSTRACT:
In order for neural network technology to make useful determinations of the identity of letters and numbers that are processed in real time at a postal service sorting center, it is necessary for the neural network to "learn" to recognize accurately the many shapes and sizes in which each letter or number are formed on the address surface of the envelope by postal service users. It has been realized that accuracy in the recognition of many letters and numbers is not appreciably sacrificed if the neural network is instructed to identify those characteristics of each letter or number which are in the category "invariant." Then, rather than requiring the neural network to recognize all gradations of shape, location, size, etc. of the identified invariant characteristic, a generalized and bounded description of the invariant segments is used which requires far less inputting of sample data and less processing of information relating to an unknown letter or number.
REFERENCES:
patent: 5058179 (1991-10-01), Denker et al.
patent: 5067164 (1991-11-01), Denker et al.
patent: 5239594 (1993-08-01), Yoda
patent: 5251268 (1993-10-01), Colley et al.
patent: 5337371 (1994-08-01), Sato et al.
patent: 5479575 (1995-12-01), Yoda
Denker John S.
LeCun Yann A.
Simard Patrice Y.
Victorri Bernard
Davis George B.
Finston Martin I.
Graves Charles E.
Lucent Technologies - Inc.
LandOfFree
Training system for neural 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 Training system for neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training system for neural networks will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2021693