Titre du document / Document title

On NIL : The software constructor of neural networks

Auteur(s) / Author(s)

SIEGELMANN H. T. ⁽¹⁾ ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

⁽¹⁾ Faculty of Industrial Engineering and Management, Technion, Haifa, 32000, ISRAEL

Résumé / Abstract

Analog recurrent neural networks have attracted much attention lately as powerful tools of automatic learning. However, they are not as popular in industry as should be justified by their usefulness. The lack of any programming tool for networks, and their vague internal representation, leave the networks for the use of experts only. We propose a way to make the neural networks friendly to users by formally defining a high level language, called Neural Information Processing Programming Langage, which is rich enough to express any computer algorithm or rule-based system. We show how to compile a NIL program into a network which computes exactly as the original program and requires the same computation/convergence time and physical size. Allowing for a natural neural evolution after the construction, the neural networks are both capable of dynamical continuous learning and represent any given symbolic knowledge. Thus, the language along with its compiler may be thought of as the ultimate bridge from symbolic to analog computation.

Revue / Journal Title

Parallel processing letters   ISSN 0129-6264 

Source / Source

1996, vol. 6, n^o4, pp. 575-582 (18 ref.)

Langue / Language

Anglais

Editeur / Publisher

World Scientific Publishing, Singapore, SINGAPOUR  (1991) (Revue)

Mots-clés anglais / English Keywords

Expert system ; Knowledge base ; Programming language ; Neural network ; Software engineering ; Knowledge representation ; Compilation ; Symbolic computation ; Syntax ; Experimental study ;

Mots-clés français / French Keywords

Système expert ; Base connaissance ; Langage programmation ; Réseau neuronal ; Génie logiciel ; Représentation connaissances ; Compilation ; Calcul symbolique ; Syntaxe ; Etude expérimentale ;

Mots-clés espagnols / Spanish Keywords

Sistema experto ; Base conocimiento ; Lenguaje programación ; Red neuronal ; Ingeniería logiciel ; Representación conocimientos ; Compilación ; Cálculo simbólico ; Sintaxis ; Estudio experimental ;

Localisation / Location

INIST-CNRS, Cote INIST : 22960, 35400006193222.0110