A high-speed integrated Hamming neural classifier

Author

Grant, David ; Taylor, John ; Houselander, Paul

Author_Institution

BNR Europe, Maidenhead, UK

Volume

6

fYear

1994

fDate

30 May-2 Jun 1994

Firstpage

479

Abstract

This paper describes a fixed-weight Hamming binary neural classifier chip suitable for applications where high-speed operation is required. The circuit uses switched current-mode techniques throughout and achieves classification in one forward pass through the network. The chip was realised in 2.4 μm n-well CMOS technology and was designed to recognise the integers 0-9. It achieved a classification rate of 10 MHz without any observable tendency to misclassification or instability

Keywords

CMOS analogue integrated circuits; analogue processing circuits; feedforward neural nets; neural chips; pattern classification; switched current circuits; 10 MHz; 2.4 micron; Hamming neural classifier; WTA network; binary neural classifier chip; fixed-weight type; high-speed integrated classifier; n-well CMOS technology; switched current-mode techniques; winner takes all network; Artificial neural networks; CMOS technology; Computer networks; Error correction; Europe; High speed integrated circuits; MOSFETs; Optical wavelength conversion; Power generation economics; Switching circuits;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on

Conference_Location

London

Print_ISBN

0-7803-1915-X

Type

conf

DOI

10.1109/ISCAS.1994.409630

Filename

409630