character recognition

Charles Wilson x2080 wilson at magi.ncsl.nist.gov
Wed Jul 18 16:05:39 EDT 1990


We have shown on character recognition problem that neural networks
are as good in accuracy as traditional methods but much faster (on a parallel
computer), much easier to prpgram ( a few hundred lines of parallel
fortran) and less brittle.

see C. L. Wilson, R. A. Wilkinson, and M. D. Garris, "self-organizing
Neural Network Character Recognition on a Massively Parallel Computer",
Proc. of the IJCNN, vol 2, pp. 325-329, June 1990.



More information about the Connectionists mailing list