Inductive learning inability of artificial neural networks

被引：0

作者：

Bhavsar, VC ^{[1
]}

Ghorbani, AA ^{[1
]}

Goldfarb, L ^{[1
]}

机构：

[1] Univ New Brunswick, Fac Comp Sci, Fredericton, NB E3B 5A3, Canada

来源：

2000 CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, CONFERENCE PROCEEDINGS, VOLS 1 AND 2: NAVIGATING TO A NEW ERA | 2000年

关键词：

neural networks; generalization; inductive learning; learning machines; pattern recognition;

D O I：

暂无

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：

The intrinsic inability of artificial neural networks to generalize from examples, i.e., to learn inductively, is exemplified based on several very simple requirements for an inductive learning machine.

引用

页码：712 / 716

页数：5

共 12 条

[1] 4 TYPES OF LEARNING-CURVES [J].

AMARI, S ;

FUJITA, N ;

SHINOMOTO, S .

NEURAL COMPUTATION, 1992, 4 (04) :605-618

[2] What Size Net Gives Valid Generalization? [J].

Baum, Eric B. ;

Haussler, David .

NEURAL COMPUTATION, 1989, 1 (01) :151-160

[3]

Denker J., 1987, Complex Systems, V1, P877

[4] CAN A VECTOR-SPACE BASED LEARNING-MODEL DISCOVER INDUCTIVE CLASS GENERALIZATION IN A SYMBOLIC ENVIRONMENT [J].

GOLDFARB, L ;

ABELA, J ;

BHAVSAR, VC ;

KAMAT, VN .

PATTERN RECOGNITION LETTERS, 1995, 16 (07) :719-726

[5]

GOLDFARB L, 1996, P WORKSH IS IND LEAR, P9

[6]

Hertz J., 1991, Introduction to the Theory of Neural Computation

[7]

HINTON GE, 1989, ARTIF INTELL, V40, P465

[8] GENERALIZATION AS SEARCH [J].

MITCHELL, TM .

ARTIFICIAL INTELLIGENCE, 1982, 18 (02) :203-226

[9] Exhaustive Learning [J].

Schwartz, D. B. ;

Samalam, V. K. ;

Solla, Sara A. ;

Denker, J. S. .

NEURAL COMPUTATION, 1990, 2 (03) :374-385

[10]

TAYLOR AE, 1987, INTRO FUNCTIONAL ANA, P1134

← 1 2 →