CONVERGENT ALGORITHMS FOR PATTERN RECOGNITION IN NONLINEARLY EVOLVING NONSTATIONARY ENVIRONMENT

被引：6

作者：

DEFIGUEIREDO, RJ

机构：

[1] Dept of Elec. Engrg., Rice University, Houston, Tex.

来源：

PROCEEDINGS OF THE INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS | 1968年 / 56卷 / 02期

关键词：

D O I：

10.1109/PROC.1968.6213

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：

Blaydon and Ho have recently proposed two algorithms to determine the probability p(A/x) that a sample with the set of attributes x belongs to a pattern class A, assuming a fixed p(A/x). The present letter modifies these algorithms to allow p(A/x) ≡p1(A/x), i=1, 2, • •, to evolve (not necessarily linearly) with i. Dynamic stochastic approximation argu¬ ments are used. Copyright © 1968 by The Institute of Electrical and Electronics Engineers, Inc.

引用

页码：188 / +

页数：1

共 8 条

[1]

Aizerman M. A., 1964, AUTOMAT REM CONTR, V25, P1546

[2]

AIZERMAN MA, 1964, AUTOMAT REM CONTR, V25, P1175

[3]

BLAYDON C, 1966, P NEC, V22, P857

[4]

DEFIGUEIREDO RJP, 1967, EE67 RICE U TECH REP

[5] A DYNAMIC STOCHASTIC-APPROXIMATION METHOD [J].

DUPAC, V .

ANNALS OF MATHEMATICAL STATISTICS, 1965, 36 (06) :1695-1702

[6]

DVORETZKY A, 1956, 3 P BERK S MATH STAT, P54

[7]

LEONDES CT, 1966, ADVANCES CONTROL ED, V3, P219

[8]

Sorenson H. W., 1966, ADV CONTROL SYST, V3, P219, DOI DOI 10.1016/B978-1-4831-6716-9.50010-2

← 1 →