Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Design and implementation of a dedicated neural network for handwritten digit recognition

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
7 Author(s)
Alla, P.-Y. ; CSI, Inst. Nat. Polytech. de Grenoble, France ; Masse-Navette, L. ; Ouali, J. ; Saucier, G.
more authors

The automatic recognition of handwritten digits seems to be one of the most promising fields for applications of artificial neural networks; various studies have shown that good recognition rates can be obtained on large 'real-world' data bases. This paper presents: (i) the design of a network architecture, resulting from a stepwise procedure developed at ESPCI for simultaneously building and training a neural network, intended for the automatic recognition of isolated handwritten digits and (ii) a silicon implementation of that network, using a general-purpose neural circuit architecture developed at CSI.<>

Published in:

Euro ASIC '91

Date of Conference:

27-31 May 1991