On-chip learning in neurocomputers

Author

Card, Howard C. ; McNeill, Dean K.

Author_Institution

Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada

Volume

1

fYear

1996

fDate

26-29 May 1996

Firstpage

182

Abstract

Artificial neural networks (ANNs) may be implemented as custom analog, digital or hybrid VLSI systems. This paper describes the tradeoffs among these approaches, based on work in our laboratory as well as at other institutions. A major theme of the work is the effects of limited precision in on-chip learning computations performed by the analog or digital circuits. Analog and low-precision digital circuits are found to be capable of reliably representing most ANN models, with area-efficient and energy-efficient implementations

Keywords

CMOS analogue integrated circuits; CMOS digital integrated circuits; VLSI; analogue processing circuits; learning (artificial intelligence); neural chips; ANN models; artificial neural networks; custom analog circuits; low-precision digital circuits; neurocomputers; onchip learning computations; Analog computers; Artificial neural networks; Cost function; Digital arithmetic; Digital circuits; Intelligent networks; Laboratories; Neural networks; Pulse amplifiers; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1996. Canadian Conference on

Conference_Location

Calgary, Alta.

ISSN

0840-7789

Print_ISBN

0-7803-3143-5

Type

conf

DOI

10.1109/CCECE.1996.548067

Filename

548067