Title
Analysis of Neural Networks with Redundancy.
Abstract
Biological systems have a large degree of redundancy, a fact that is usually thought to have little effect beyond providing reliable function despite the death of individual neurons. We have discovered, however, that redundancy can qualitatively change the computations carried out by a network. We prove that for both feedforward and feedback networks the simple duplication of nodes and connections...
Year
DOI
Venue
1990
10.1162/neco.1990.2.2.226
Neural Computation
Keywords
Field
DocType
neural network,reliability function,biological systems
Computer science,Theoretical computer science,Redundancy (engineering),Artificial intelligence,Dual modular redundancy,Artificial neural network,Machine learning,Computation,Feed forward
Journal
Volume
Issue
ISSN
2
2
0899-7667
Citations 
PageRank 
References 
21
3.58
0
Authors
2
Name
Order
Citations
PageRank
Yoshio Izui1306.07
Alex Pentland2180064853.13