LOCAL FEEDBACK MULTILAYERED NETWORKS

被引：115

作者：

FRASCONI, P ^{[1
]}

GORI, M ^{[1
]}

SODA, G ^{[1
]}

机构：

[1] DIPARTIMENTO SISTEMI & INFORMAT,I-50139 FLORENCE,ITALY

来源：

NEURAL COMPUTATION | 1992年 / 4卷 / 01期

关键词：

D O I：

10.1162/neco.1992.4.1.120

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we investigate the capabilities of local feedback multilayered networks, a particular class of recurrent networks, in which feedback connections are only allowed from neurons to themselves. In this class, learning can be accomplished by an algorithm that is local in both space and time. We describe the limits and properties of these networks and give some insights on their use for solving practical problems.

引用

页码：120 / 130

页数：11

共 16 条

[1] LINKS BETWEEN MARKOV-MODELS AND MULTILAYER PERCEPTRONS [J].

BOURLARD, H ;

WELLEKENS, CJ .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (12) :1167-1178

[2] Finite State Automata and Simple Recurrent Networks [J].

Cleeremans, Axel ;

Servan-Schreiber, David ;

McClelland, James L. .

NEURAL COMPUTATION, 1989, 1 (03) :372-381

[3]

ELMAN JL, 1988, CRL8801 U CAL CTR RE

[4]

FRASCONI P, 1991, RT291 U FIR DIP SIST

[5]

FRASCONI P, 1990, 3RD P IT WORKSH PAR, P329

[6]

GHERRITY M, 1989, JUN P IEEE IJCNN 89, V643

[7]

GORI M, 1990, THESIS U BOLOGNA ITA

[8]

GORI M, 1989, 1989 P NEUR NIM 89, P83

[9]

GORI M, 1989, P INT JOINT C NEURAL, V2, P417

[10]

MOZER MC, 1988, CRGTR883 U TOR TECH

← 1 2 →