A modified current mode Hamming neural network for totally unconstrained handwritten numeral recognition

Author

Guoxing, LI ; Bingxue, Shi ; Wei, Lu

Author_Institution

Inst. of Microelectron., Tsinghua Univ., Beijing, China

Volume

3

fYear

1998

fDate

4-9 May 1998

Firstpage

1857

Abstract

A compact smart current mode Hamming neural network for classifying complex patterns such as totally unconstrained handwritten digits is presented. It is based on multi-threshold template matching, multistage matching and k-WTB (k-winner-taker-all). The neural classifier consists of two kinds of templates: one is a binary template and the other is a multi-value programmable template, each of them has its own threshold and realized in MOS current mirrors, the current mode k-WTA which is reconfigurable is put forward. The second stage matching templates are programmable from outside the chip. This mixed analog-digital Hamming neural classifier can be fabricated in a standard digital CMOS technology

Keywords

CMOS integrated circuits; amplifiers; character recognition; mixed analogue-digital integrated circuits; neural chips; pattern classification; MOS current mirrors; binary template; complex patterns; k-winner-taker-all; mixed analog-digital Hamming neural classifier; modified current mode Hamming neural network; multi-threshold template matching; multi-value programmable template; multistage matching; neural classifier; second stage matching templates; standard digital CMOS technology; totally unconstrained handwritten numeral recognition; Clocks; Counting circuits; Decoding; EPROM; Finishing; Force control; Handwriting recognition; Latches; Neural networks; Programmable logic arrays;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.687140

Filename

687140