CMOS current-mode outstar neural networks with long-period analog ratio memory

Author

Lan, Jeng-Feng ; Wu, Chung-Yu

Author_Institution

Dept. of Electron. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan

Volume

3

fYear

1995

fDate

30 Apr-3 May 1995

Firstpage

1676

Abstract

An on-chip learnable neural network called the outstar is implemented in CMOS current-mode circuits. The on-chip memory called the ratio memory can retain the stored ratio values. The outstar chip is fabricated and tested. It has shown that the storage time of the ratio memory can be as long as 5 minutes without refreshment. Moreover, the outstar can normalize the input pattern and enhance the contrast of the stored pattern within a long period. The application of the outstar in pattern classification has been demonstrated

Keywords

CMOS analogue integrated circuits; analogue processing circuits; analogue storage; image processing equipment; neural chips; pattern classification; pattern recognition equipment; CMOS current-mode circuits; current-mode neural networks; long-period analog ratio memory; onchip learnable neural network; onchip memory; outstar chip; pattern classification; stored pattern; Analog integrated circuits; Capacitors; Electronic mail; Equations; Laboratories; Mathematical model; Network-on-a-chip; Neural networks; Neurons; Pattern classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2570-2

Type

conf

DOI

10.1109/ISCAS.1995.523733

Filename

523733