DocumentCode :
278002
Title :
Neural networks: problems and opportunities!
Author :
Noakes, P.D. ; Green, A.D.P.
Author_Institution :
Dept. of Electron. Syst. Eng., Essex Univ., Colchester, UK
fYear :
1991
fDate :
33309
Firstpage :
42370
Lastpage :
42373
Abstract :
Artificial neural networks attempt to model the massively parallel structure and the learning capability offered by biological neural systems. They have been shown to offer significant advantages over conventional processing techniques in certain recognition and control applications. However there are problems in selecting an appropriate neuron model and network configuration. The paper discusses these problems and identifies the need to establish a design methodology for neural systems
Keywords :
neural nets; control applications; design methodology; learning capability; massively parallel structure; network configuration; neural networks; neuron model; recognition;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Neural Networks: Design Techniques and Tools, IEE Colloquium on
Conference_Location :
London
Type :
conf
Filename :
181066
Link To Document :
بازگشت