INDUCTION OF FINITE-STATE LANGUAGES USING 2ND-ORDER RECURRENT NETWORKS

被引：69

作者：

WATROUS, RL ^{[1
]}

KUHN, GM ^{[1
]}

机构：

[1] INST DEF ANAL,CTR COMMUN RES,PRINCETON,NJ 08540

来源：

NEURAL COMPUTATION | 1992年 / 4卷 / 03期

关键词：

D O I：

10.1162/neco.1992.4.3.406

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Second-order recurrent networks that recognize simple finite state languages over {0,1}* are induced from positive and negative examples. Using the complete gradient of the recurrent network and sufficient training examples to constrain the definition of the language to be induced, solutions are obtained that correctly recognize strings of arbitrary length.

引用

页码：406 / 414

页数：9

共 10 条

[1] [Anonymous], 2016, LINEAR NONLINEAR PRO
[2] Finite State Automata and Simple Recurrent Networks
Cleeremans, Axel
Servan-Schreiber, David
McClelland, James L.
[J]. NEURAL COMPUTATION, 1989, 1 (03) : 372 - 381
[3] FINDING STRUCTURE IN TIME
ELMAN, JL
[J]. COGNITIVE SCIENCE, 1990, 14 (02) : 179 - 211
[4] GILES CL, 1990, ADV NEURAL INFORM PR, V0002, P00380
[5] GILES CL, 1991, 2 P INT JOINT C NEUR, P273
[6] POLLACK J, 1991, COMMUNICATION
[7] POLLACK JB, 1990, 90JPAUTOMATA OH STAT
[8] TOMITA M, 1982, 4TH P ANN COGN SCI C, P105
[9] COMPLETE GRADIENT OPTIMIZATION OF A RECURRENT NETWORK APPLIED TO B,D,G DISCRIMINATION
WATROUS, RL
LADENDORF, B
KUHN, G
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1990, 87 (03) : 1301 - 1309
[10] WILLIAMS RJ, 1988, ICS8805 UCSD I COGN

← 1 →