A composition of the neural network using switched-capacitor circuit

Author

Sasaki, M. ; Ueno, F. ; Inoue, T. ; Haraguti, N.

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Kumamoto Univ., Japan

fYear

1992

fDate

17-19 Sep 1992

Firstpage

40

Lastpage

43

Abstract

A switched-capacitor (SC) neural network is described. The motion of the SC neural network is represented with stochastic difference equations. The network consists of two-state neurons (ON-OFF neurons). The equations can lead to a convergence to global minima even with the two-state neurons by introducing the technique of simulated annealing. The two-state neurons make the circuits of the activation function and multiplication very simple. The network limitation of the SC neural network is analyzed in detail, and the circuit performance of 32.8 GCPS is confirmed. The computational capacity of the SC neural network is confirmed in connection with the solution of an optimization problem

Keywords

difference equations; neural nets; simulated annealing; switched capacitor networks; ON-OFF neurons; activation function; computational capacity; convergence; multiplication; neural network; optimization; simulated annealing; stochastic difference equations; switched-capacitor circuit; two-state neurons; Circuit optimization; Circuit simulation; Computational modeling; Convergence; Difference equations; Neural networks; Neurons; Performance analysis; Simulated annealing; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems Engineering, 1992., IEEE International Conference on

Conference_Location

Kobe

Print_ISBN

0-7803-0734-8

Type

conf

DOI

10.1109/ICSYSE.1992.236947

Filename

236947