FUZZY-SYSTEMS AS UNIVERSAL APPROXIMATORS

被引：488

作者：

KOSKO, B

机构：

[1] Department of Electrical Engineering-Systems, Signal and Image Processing Institute, University of Southern California, Los Angeles, CA 90089-2564, 3740 McClintock Avenue

来源：

IEEE TRANSACTIONS ON COMPUTERS | 1994年 / 43卷 / 11期

关键词：

D O I：

10.1109/12.324566

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

An additive fuzzy system can uniformly approximate any real continuous function on a compact domain to any degree of accuracy. An additive fuzzy system approximates the function by covering its graph with fuzzy patches in the input-output state space and averaging patches that overlap. The fuzzy system computes a conditional expectation E[Y \ X] if we view the fuzzy sets as random sets. Each fuzzy rule defines a fuzzy patch and connects commonsense knowledge with state-space geometry. Neural or statistical clustering systems can approximate the unknown fuzzy patches from training data. These adaptive fuzzy systems approximate a function at two levels. At the local level the neural system approximates and tunes the fuzzy rules. At the global level the rules or patches approximate the function.

引用

页码：1329 / 1333

页数：5

共 12 条

[1]

[Anonymous], 1989, ANALOG VLSI NEURAL S

[2]

DICKERSON JA, 1993, JUL WORLD C NEUR NET, V2, P9

[3]

Dubois, 1980, FUZZY SETS FUZZY SYS

[4] Layered Neural Networks with Gaussian Hidden Units as Universal Approximations [J].

Hartman, Eric J. ;

Keeler, James D. ;

Kowalski, Jacek M. .

NEURAL COMPUTATION, 1990, 2 (02) :210-215

[5] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1989, 2 (05) :359-366

[6] STOCHASTIC COMPETITIVE LEARNING [J].

KOSKO, B .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (05) :522-529

[7]

Kosko B., 1986, INT J INTELL SYST, V1, P293, DOI 10.1002/int.4550010405

[8]

Kosko B., 1991, NEURAL NETWORKS FUZZ

[9]

Rudin W., 1973, FUNCTIONAL ANAL

[10] FUZZY BASIS FUNCTIONS, UNIVERSAL APPROXIMATION, AND ORTHOGONAL LEAST-SQUARES LEARNING [J].

WANG, LX ;

MENDEL, JM .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05) :807-814

← 1 2 →