Title
Making competition in neural fields suitable for computational architectures
Abstract
In this paper, a new competition mechanism for neural fields is proposed, as well as first experimental studies of its robustness. The computational properties of this algorithm are discussed, arguing that such properties are suitable for neural architectures, where some restrictions of the usual neural fields competition methods are not acceptable.
Year
DOI
Venue
2005
10.1007/11550822_35
ICANN (1)
Keywords
Field
DocType
usual neural fields competition,neural field,experimental study,neural architecture,computational architecture,computational property,new competition mechanism,computer architecture
Physical neural network,Computer science,Models of neural computation,Neural fields,Robustness (computer science),Unsupervised learning,Artificial intelligence,Artificial neural network,Spiking neural network,Machine learning
Conference
Volume
ISSN
ISBN
3696
0302-9743
3-540-28752-3
Citations 
PageRank 
References 
3
0.47
2
Authors
2
Name
Order
Citations
PageRank
Hervé Frezza-Buet18010.20
Olivier Ménard2111.54