FORMAL NEURAL-NETWORK SPECIFICATION AND ITS IMPLICATIONS ON STANDARDIZATION

被引：6

作者：

DORFFNER, G ^{[1
]}

WIKLICKY, H ^{[1
]}

PREM, E ^{[1
]}

机构：

[1] AUSTRIAN RES INST ARTIFICIAL INTELLIGENCE,A-1010 VIENNA,AUSTRIA

来源：

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

关键词：

ARTIFICIAL NEURAL NETWORKS; SPECIFICATION; FORMAL DESCRIPTION; NEURAL NETWORK PARADIGMS; COMPARISON;

D O I：

10.1016/0920-5489(94)90012-4

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper introduces a formal framework for describing and specifying neural networks and discusses several important issues with implications for neural network standardization. In particular, a neural network definition and two tools for graphical description and formal specification are introduced. Issues such as the theoretical impossibility of canonical description, or the need for complete specification (including global algorithms) are discussed. Several examples, making use of the developed tools, illustrate these discussions. In summary, this paper aims at contributing to the important endeavour of neural network standardization both practically and theoretically.

引用

页码：205 / 219

页数：15

共 28 条

[1]

Agha GA, 1990, ACTORS MODEL CONCURR

[2]

ANDERSON JA, 1988, NEUROCOMPUTING, V1

[3]

BOTTOU L, 1992, P INT JOINT C NEURAL, P7

[4]

BOTTOU L, 1990, ADV NEURAL INFORMATI, V3, P781

[5]

DEROT B, 1989, P NEUR 89 NIM FRANC, P183

[6]

Fiesler E, 1992, NEURAL NETWORK FORMA

[7] A UNIFIED FRAMEWORK FOR CONNECTIONIST SYSTEMS [J].

GOLDEN, RM .

BIOLOGICAL CYBERNETICS, 1988, 59 (02) :109-120

[8]

GOLES E, 1990, MATH ITS APPLICATION, V58

[9] ADAPTIVE PATTERN-CLASSIFICATION AND UNIVERSAL RECODING .1. PARALLEL DEVELOPMENT AND CODING OF NEURAL FEATURE DETECTORS [J].

GROSSBERG, S .

BIOLOGICAL CYBERNETICS, 1976, 23 (03) :121-134

[10]

GROSSBERG S, 1988, NEUROCOMPUTING, V1

← 1 2 3 →