Morphologically realistic neural networks

This paper presents how morphologically more realistic artificial neural networks have been obtained by using vectorial-stochastic grammars and used as subsidies for modeling biological neural systems and developing novel artificial neural structures. The paper includes the description of the vector...

Full description

Saved in:
Bibliographic Details
Published inProceedings. Third IEEE International Conference on Engineering of Complex Computer Systems (Cat. No.97TB100168) pp. 223 - 228
Main Authors Coelho, R.C., da Fontoura Costa, L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1997
Subjects
Artificial neural networks
Biological system modeling
Brain modeling
Cybernetics
Encoding
Morphology
Neural networks
Neurons
Production
Shape
Online AccessGet full text

Cover

More Information
Summary:This paper presents how morphologically more realistic artificial neural networks have been obtained by using vectorial-stochastic grammars and used as subsidies for modeling biological neural systems and developing novel artificial neural structures. The paper includes the description of the vectorial-stochastic grammars, a review of the primate striate cortex, a mathematical analysis of the principles underlying orientation encoding by centric domains, and the development and application of morphologically realistic neural centric models of orientation encoding.
ISBN:0818681268
9780818681264
DOI:10.1109/ICECCS.1997.622314