ON THE INFORMATION-STORAGE CAPACITY OF LOCAL LEARNING RULES

被引：16
作者：
PALM, G
机构：
来源：
NEURAL COMPUTATION | 1992年 / 4卷 / 05期
关键词：
D O I：
10.1162/neco.1992.4.5.703
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A simple relation between the storage capacity A for autoassociation and H for heteroassociation with a local learning rule is demonstrated: H = 2A. Both values are bounded by local learning bounds: A less-than-or-equal-to L(A) and H less-than-or-equal-to L(H). L(H) = 2L(A) is evaluated numerically.
引用
收藏
页码：703 / 711
页数：9
相关论文
共 10 条
[1]   INFORMATION-STORAGE IN NEURAL NETWORKS WITH LOW-LEVELS OF ACTIVITY [J].
AMIT, DJ ;
GUTFREUND, H ;
SOMPOLINSKY, H .
PHYSICAL REVIEW A, 1987, 35 (05) :2293-2303
[2]   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
[3]   NEURAL NETWORKS WITH LOW-LEVELS OF ACTIVITY - ISING VS MCCULLOCH-PITTS NEURONS [J].
HORNER, H .
ZEITSCHRIFT FUR PHYSIK B-CONDENSED MATTER, 1989, 75 (01) :133-136
[4]   Information storage in sparsely coded memory nets [J].
Nadal, Jean-Pierre ;
Toulouse, Gerard .
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1990, 1 (01) :61-74
[5]  
PALM G, 1980, BIOL CYBERN, V36, P19, DOI 10.1007/BF00337019
[6]  
PALM G, 1990, ADVANCED NEURAL COMPUTERS, P145
[7]  
PALM G, 1982, CYBERNET SYST, P277
[8]  
PALM G, 1988, NEURAL COMPUTERS, P271
[9]   THE ENHANCED STORAGE CAPACITY IN NEURAL NETWORKS WITH LOW ACTIVITY LEVEL [J].
TSODYKS, MV ;
FEIGELMAN, MV .
EUROPHYSICS LETTERS, 1988, 6 (02) :101-105
[10]   Optimal Plasticity from Matrix Memories: What Goes Up Must Come Down [J].
Willshaw, David ;
Dayan, Peter .
NEURAL COMPUTATION, 1990, 2 (01) :85-93
1