A PULSED NEURAL NETWORK CAPABLE OF UNIVERSAL APPROXIMATION

被引：5

作者：

COTTER, NE

MIAN, ON

机构：

[1] Electrical Engineering Department, University of Utah, Salt Lake City

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1992年 / 3卷 / 02期

关键词：

D O I：

10.1109/72.125872

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes a pulsed network version of the cerebellar model articulation controller (CMAC), popularized by Albus. The network produces output pulses whose times of occurrence are a function of input pulse intervals. Within limits imposed by causality conditions, this function can approximate any bounded measurable function on a compact domain. Simulation results demonstrate the viability of training the network with a least mean squares algorithm.

引用

页码：308 / 314

页数：7

共 22 条

[1]

ALBUS JS, 1981, BRAINS BEHAVIOR ROBO

[2]

BORISYUK GN, 1990, JUN P IEEE INT C NEU, V2, P431

[3]

DAYHOFF JE, 1990, JUN P IEEE INT C NEU, V3, P621

[4]

DAYHOFF JE, 1987, 1ST P IEEE INT C NEU, V3, P63

[5]

FATT P, 1952, J PHYSIOL-LONDON, V117, P109

[6] SIMULATION OF CHAOTIC EEG PATTERNS WITH A DYNAMIC-MODEL OF THE OLFACTORY SYSTEM [J].

FREEMAN, WJ .

BIOLOGICAL CYBERNETICS, 1987, 56 (2-3) :139-150

[7]

GLUCK M, 1989, ADV NEURAL INFORMATI, V1, P195

[8]

GOERKE N, 1990, JUN P IEEE INT C NEU, V3, P315

[9] NEURONS WITH GRADED RESPONSE HAVE COLLECTIVE COMPUTATIONAL PROPERTIES LIKE THOSE OF 2-STATE NEURONS [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1984, 81 (10) :3088-3092

[10]

Hoppensteadt F.C, 1997, INTRO MATH NEURONS M

← 1 2 3 →