Similarity, connectionism, and the problem of representation in vision

被引：25

作者：

Edelman, S

DuvdevaniBar, S

机构：

[1] Dept. of Appl. Math. and Comp. Sci., Weizmann Institute of Science

来源：

NEURAL COMPUTATION | 1997年 / 9卷 / 04期

关键词：

D O I：

10.1162/neco.1997.9.4.701

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A representational scheme under which the ranking between represented similarities is isomorphic to the ranking between the corresponding shape similarities can support perfectly correct shape classification because it preserves the clustering of shapes according to the natural kinds prevailing in the external world. This article discusses the computational requirements of representation that preserves similarity ranks and points out the relative straightforwardness of its connectionist implementation.

引用

页码：701 / 720

页数：20

共 49 条

[1] SHIFTER CIRCUITS - A COMPUTATIONAL STRATEGY FOR DYNAMIC ASPECTS OF VISUAL PROCESSING [J].