Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Journal of Integrative Neuroscience, Vol. 2, No. 1 (2003) 5569 c Imperial College Press
 

Summary: Journal of Integrative Neuroscience, Vol. 2, No. 1 (2003) 5569
c Imperial College Press
A MODEL FOR EMERGENT COMPLEX ORDER
IN SMALL NEURAL NETWORKS
PETER ANDRAS
Claremont Tower, School of Computing Science,
University of Newcastle, Newcastle upon Tyne, NE1 7RU, UK
peter.andras@ncl.ac.uk
Received 17 March 2003
Revised 15 April 2003
A new neural network model is introduced in this paper. The aim of the proposed Sierpinski
neural networks is to provide a simple and biologically plausible neural network architec-
ture that produces emergent complex spatio-temporal patterns through the activity of the
output neurons of the network and is able to perform computational tasks. Such networks
may play an important role in the analysis and understanding of complex dynamic activity
observed at various levels of biological neural systems. The proposed Sierpinski neural net-
works are described in detail and their functioning is analyzed. We discuss about emerging
neural activity patterns and their interpretations, neuro-computation with such emerging
activity patterns, and also possible implications for computational neuroscience.
Keywords: Complex emergent behavior; dynamic patterns; neural network model; Sierpin-

  

Source: Andras, Peter - School of Computing Science, University of Newcastle upon Tyne
Newcastle upon Tyne, University of - School of Computing Science

 

Collections: Computer Technologies and Information Sciences