MATHEMATICAL FOUNDATIONS OF NEUROCOMPUTING

被引：115

作者：

AMARI, S

机构：

[1] Faculty of Engineering, University of Tokyo

来源：

PROCEEDINGS OF THE IEEE | 1990年 / 78卷 / 09期

关键词：

D O I：

10.1109/5.58324

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：

Neurocomputing makes use of parallel dynamical interactions of modifiable neuron-like elements. It is important to show, by mathematical treatments, the capabilities and limitations of information processing by various architectures of neural networks. This paper, part tutorial and part review, tries to give mathematical foundations to neurocomputing. It considers the capabilities of transformations by layered networks, statistical neurodynamics, the dynamical characteristics of associative memory, a general theory of neural learning, and self-organization of neural networks. © 1990 IEEE

引用

页码：1443 / 1463

页数：21

共 77 条

[1]

ALMEIDA LB, 1987, 1ST P IEEE INT C NEU, V2, P609

[2] CHARACTERISTICS OF SPARSELY ENCODED ASSOCIATIVE MEMORY [J].

AMARI, S .

NEURAL NETWORKS, 1989, 2 (06) :451-457

[3] CHARACTERISTICS OF RANDOM NETS OF ANALOG NEURON-LIKE ELEMENTS [J].

AMARI, S .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1972, SMC2 (05) :643-&

[4]

AMARI S, 1980, B MATH BIOL, V42, P339

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

AMARI, S .

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

[6] STATISTICAL NEURODYNAMICS OF ASSOCIATIVE MEMORY [J].

AMARI, S ;

MAGINU, K .

NEURAL NETWORKS, 1988, 1 (01) :63-73

[7]

AMARI S, 1968, GEOMETRICAL THEORY I

[8]

AMARI S, 1988, SPRINGER SERIES SYNE, V42, P85

[9]

Amari S., 1977, SYSTEMS NEUROSCIENCE, P119, DOI DOI 10.1016/B978-0-12-491850-4.50009-X

[10]

AMARI S, 1988, SPRINGER RES NOTES N, V1, P15

← 1 2 3 4 5 6 7 8 →