Digital design of sigmoid approximator for artificial neural networks

被引：27

作者：

Basterretxea, K

Tarela, JM

del Campo, I

机构：

[1] Euskal Herriko Unibertsitatea, EHU,UPV, EUITI, Elekt & Telekomunikazio Saila,, Bilbao 48012, Basque Country, Spain

[2] Euskal Herriko Unibertsitatea, UPV, EHU, Zientzi Fak, Leioa 48940, Basque Country, Spain

来源：

ELECTRONICS LETTERS | 2002年 / 38卷 / 01期

关键词：

D O I：

10.1049/el:20020008

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A digital design for piecewise-linear (PWL) approximation to the sigmoid function is presented. Circuit operation is based on a recursive algorithm that uses lattice operators max and min to approximating nonlinear functions. The resulting hardware is programmable, allowing for the control of the delay-time/approximation-accuracy rate.

引用

页码：35 / 37

页数：3

共 6 条

[1]

ALIPPI C, 1991, P IEEE INT S CIRC SY, P1505

[2] Piecewise linear approximation applied to nonlinear function of a neural network [J].

Amin, H ;

Curtis, KM ;

Hayes-Gill, BR .

IEE PROCEEDINGS-CIRCUITS DEVICES AND SYSTEMS, 1997, 144 (06) :313-317

[3] IMPLEMENTATION ISSUES OF SIGMOID FUNCTION AND ITS DERIVATIVE FOR VLSI DIGITAL NEURAL NETWORKS [J].

MURTAGH, P ;

TSOI, AC .

IEE PROCEEDINGS-E COMPUTERS AND DIGITAL TECHNIQUES, 1992, 139 (03) :207-214

[4] EFFICIENT IMPLEMENTATION OF PIECEWISE LINEAR ACTIVATION FUNCTION FOR DIGITAL VLSI NEURAL NETWORKS [J].

MYERS, DJ ;

HUTCHINSON, RA .

ELECTRONICS LETTERS, 1989, 25 (24) :1662-1663

[5]

TARELA JM, IN PRESS MATH COMPUT

[6] Sigmoid generators for neural computing using piecewise approximations [J].

Zhang, M ;

Vassiliadis, S ;

DelgadoFrias, JG .

IEEE TRANSACTIONS ON COMPUTERS, 1996, 45 (09) :1045-1049

← 1 →