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

Author

Alla, P.-Y. ; Masse-Navette, L. ; Ouali, J. ; Saucier, G. ; Knerr, S. ; Personnaz, L. ; Dreyfus, G.

Author_Institution

CSI, Inst. Nat. Polytech. de Grenoble, France

fYear

1991

fDate

27-31 May 1991

Firstpage

63

Lastpage

67

Abstract

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.<>

Keywords

character recognition; neural nets; parallel architectures; CSI; ESPCI; dedicated neural network; general-purpose neural circuit architecture; handwritten digit recognition; isolated handwritten digits; network architecture; recognition rates; stepwise procedure; Artificial neural networks; Backpropagation; Buildings; Circuits; Handwriting recognition; Industrial training; Neural networks; Neurons; Piecewise linear techniques; Silicon;

fLanguage

English

Publisher

ieee

Conference_Titel

Euro ASIC '91

Conference_Location

Paris, France

Print_ISBN

0-8186-2185-0

Type

conf

DOI

10.1109/EUASIC.1991.212892

Filename

212892