ANALYSIS OF LEARNING-PROCESSES OF CHAOTIC TIME-SERIES BY NEURAL NETWORKS

被引：22

作者：

HONDOU, T

SAWADA, Y

机构：

来源：

PROGRESS OF THEORETICAL PHYSICS | 1994年 / 91卷 / 02期

关键词：

D O I：

10.1143/PTP.91.397

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

Study of the learning process of chaotic time series by neural networks with back-propagation algorithm showed the existence of a general learning process. The process was found to be efficiently characterized by newly defined normalized measures, the coherence and the direction-cosine for the motion of weight vectors.

引用

页码：397 / 402

页数：6

共 16 条

[1] A THEORY OF ADAPTIVE PATTERN CLASSIFIERS [J].

AMARI, S .

IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS, 1967, EC16 (03) :299-+

[2]

[Anonymous], 1989, MODELING BRAIN FUNCT

[3]

DOYA K, 1989, 3RD P IJCNN, V1, P27

[4] ON THE APPROXIMATE REALIZATION OF CONTINUOUS-MAPPINGS BY NEURAL NETWORKS [J].

FUNAHASHI, K .

NEURAL NETWORKS, 1989, 2 (03) :183-192

[5] LEARNING IN NEURAL NETWORKS WITH LOCAL MINIMA [J].

HESKES, TM ;

SLIJPEN, ETP ;

KAPPEN, B .

PHYSICAL REVIEW A, 1992, 46 (08) :5221-5231

[6]

HONDOU T, 1993, P IJCNN NAGOYA, P2387

[7] DYNAMICS OF LEARNING AND GENERALIZATION IN A BINARY PERCEPTRON MODEL [J].

HORNER, H .

ZEITSCHRIFT FUR PHYSIK B-CONDENSED MATTER, 1992, 87 (03) :371-376

[8]

McClelland J. L., 1986, PARALLEL DISTRIBUTED, V1

[9]

McGeoch JA, 1952, PSYCHOL HUMAN LEARNI

[10] Fast Learning in Networks of Locally-Tuned Processing Units [J].

Moody, John ;

Darken, Christian J. .

NEURAL COMPUTATION, 1989, 1 (02) :281-294

← 1 2 →