FORMING SPARSE REPRESENTATIONS BY LOCAL ANTI-HEBBIAN LEARNING

被引：347

作者：

FOLDIAK, P

机构：

[1] Physiological Laboratory, University of Cambridge, Cambridge, CB2 3EG, Downing Street

来源：

BIOLOGICAL CYBERNETICS | 1990年 / 64卷 / 02期

关键词：

D O I：

10.1007/BF02331346

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

How does the brain form a useful representation of its environment? It is shown here that a layer of simple Hebbian units connected by modifiable anti-Hebbian feed-back connections can learn to code a set of patterns in such a way that statistical dependency between the elements of the representation is reduced, while information is preserved. The resulting code is sparse, which is favourable if it is to be used as input to a subsequent supervised associative layer. The operation of the network is demonstrated on two simple problems. © 1990 Springer-Verlag.

引用

页码：165 / 170

页数：6

共 19 条

[1]

[Anonymous], 1987, LEARNING INTERNAL RE

[2]

BARLOW H, 1989, COMP NEUR S, P54

[3]

Barlow H, 1985, MODELS VISUAL CORTEX, P37

[4]

Barlow H., 1961, SENS COMMUN, P217, DOI DOI 10.7551/MITPRESS/9780262518420.003.0013