ROBUSTNESS IN MULTILAYER PERCEPTRONS

被引：32

作者：

KERLIRZIN, P

VALLET, F

机构：

来源：

NEURAL COMPUTATION | 1993年 / 5卷 / 03期

关键词：

D O I：

10.1162/neco.1993.5.3.473

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we study the robustness of multilayer networks versus the destruction of neurons. We show that the classical backpropagation algorithm does not lead to optimal robustness and we propose a modified algorithm that improves this capability.

引用

收藏

页码：473 / 482

页数：10

相关论文

共 10 条

[1] STORING INFINITE NUMBERS OF PATTERNS IN A SPIN-GLASS MODEL OF NEURAL NETWORKS [J].

AMIT, DJ ;

GUTFREUND, H ;

SOMPOLINSKY, H .

PHYSICAL REVIEW LETTERS, 1985, 55 (14) :1530-1533

[2]

COTTRELL DM, 1987, ADV COGNITIVE SCI, V3

[3] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558

[4]

KERLIRZIN P, 1990, LCR ASRF908 RAPP STA

[5]

Lecun Y., 1987, THESIS U P M CURIE P

[6]

McClelland JL, 1986, PARALLEL DISTRIBUTED, V1, P1

[7]

Rumelhart D.E., 1986, PARALLEL DISTRIBUTED, DOI 10.7551/mitpress/5236.001.0001

[8] RECOGNITION RATES OF THE HEBB RULE FOR LEARNING BOOLEAN FUNCTIONS [J].

VALLET, F ;

CAILTON, JG .

PHYSICAL REVIEW A, 1990, 41 (06) :3059-3065

[9] THEORY OF ASSOCIATIVE MEMORY IN RANDOMLY CONNECTED BOOLEAN NEURAL NETWORKS [J].

WONG, KYM ;

SHERRINGTON, D .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1989, 22 (12) :2233-2263

[10]

1988, NEURAL NETWORK STUDY