A single layer training for high speed character recognition

Author

Abo-Elsoud, Mohy A. ; Soliman, Hassan H. ; El-Bakry, Hazem M. ; El-Mikati, Haindi A.

Author_Institution

Electron. & Elect. Comm. Dept., Mansoura Univ., Egypt

fYear

1996

fDate

19-21 Mar 1996

Firstpage

321

Lastpage

328

Abstract

Single-layer training for high speed English capital or small letters recognition is presented. A new approach to the hardware implementation of the artificial processing element (PE) and control circuits with learning is introduced. The programmable synaptic weights are computed during the training period by a software program. The proposed learning algorithm is very fast and significant in many ways. The results are computed in real time and appear to be perfect. This system is very suitable for analog-digital VLSI implementation

Keywords

CMOS analogue integrated circuits; VLSI; image recognition; learning (artificial intelligence); neural chips; optical character recognition; real-time systems; analog-digital VLSI implementation; artificial processing element; control circuits; hardware implementation; high speed character recognition; learning algorithm; programmable synaptic weights; real time computing; single layer training; software program; Analog-digital conversion; Character recognition; Circuits; Detectors; Multi-layer neural network; Multilayer perceptrons; Neural network hardware; Neural networks; Pattern recognition; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Radio Science Conference, 1996. NRSC '96., Thirteenth National

Conference_Location

Cairo

Print_ISBN

0-7803-3656-9

Type

conf

DOI

10.1109/NRSC.1996.551123

Filename

551123