ePrints

Analog design of a new neural network for optical character recognition

Lookup NU author(s): Ian Morns, Emeritus Professor Satnam Dlay

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy.

Publication metadata

Author(s): Morns IP, Dlay SS

Publication type: Article

Publication status: Published

Journal: IEEE Transactions on Neural Networks

Year: 1999

Volume: 10

Issue: 4

Pages: 951-953

Print publication date: 01/07/1999

ISSN (print): 2162-237X

ISSN (electronic): 1045-9227

Publisher: IEEE

URL: http://dx.doi.org/10.1109/72.774269

DOI: 10.1109/72.774269

Altmetrics

Share