DocumentCode
2388761
Title
Morphologically realistic neural networks
Author
Coelho, Regina Gélia ; da Fontoura Costa, L.
Author_Institution
Cybern. Vision Res. Group, IFSC-USP, Sao Carlos, Brazil
fYear
1997
fDate
8-12 Sep 1997
Firstpage
223
Lastpage
228
Abstract
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
Keywords
encoding; grammars; mathematical analysis; neural nets; artificial neural networks; biological neural systems; mathematical analysis; morphologically realistic neural networks; neural centric models; orientation encoding; primate striate cortex; vectorial-stochastic grammars; Artificial neural networks; Biological system modeling; Brain modeling; Cybernetics; Encoding; Morphology; Neural networks; Neurons; Production; Shape;
fLanguage
English
Publisher
ieee
Conference_Titel
Engineering of Complex Computer Systems, 1997. Proceedings., Third IEEE International Conference on
Conference_Location
Como
Print_ISBN
0-8186-8126-8
Type
conf
DOI
10.1109/ICECCS.1997.622314
Filename
622314
Link To Document