NEURAL-NETWORK CLASSIFICATION AND FORMALIZATION

被引：20

作者：

FIESLER, E ^{[1
]}

机构：

[1] IDIAP,CH-1920 MARTIGNY,SWITZERLAND

来源：

COMPUTER STANDARDS & INTERFACES | 1994年 / 16卷 / 03期

关键词：

(ARTIFICIAL) NEURAL NETWORK; NEURAL COMPUTING; NEUROCOMPUTING; CONNECTIONISM; FORMALIZATION; TERMINOLOGY; NOMENCLATURE; MNEMONIC NOTATION; TOPOLOGICAL TAXONOMY; NEURAL NETWORK CLASSIFICATION; NEURAL NETWORK DETERMINATION;

D O I：

10.1016/0920-5489(94)90014-0

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In order to assist the field of neural networks in maturing, a formalization and a solid foundation are essential. Additionally, to permit the introduction of formal proofs, it is essential to have an all-encompassing formal mathematical definition of a neural network. This publication offers a neural network formalization consisting of a topological taxonomy, a uniform nomenclature, and an accompanying consistent mnemonic notation. Supported by this formalization, both a flexible hierarchical and a universal mathematical definition are presented.

引用

页码：231 / 239

页数：9

共 21 条

[1] DISTINCTIVE FEATURES, CATEGORICAL PERCEPTION, AND PROBABILITY-LEARNING - SOME APPLICATIONS OF A NEURAL MODEL [J].