How Inhibitory Oscillations Can Train Neural Networks and Punish Competitors

We present a new learning algorithm that leverages oscillations in the strength of neural inhibition to train neural networks. Raising inhibition can be used to identify weak parts of target memories, which are then strengthened. Conversely, lowering inhibition can be used to identify competitors, w...

Full description

Saved in:
Bibliographic Details
Published in:Neural computation 2006-07, Vol.18 (7), p.1577-1610
Main Authors: Norman, Kenneth A, Newman, Ehren, Detre, Greg, Polyn, Sean
Format: Article
Language:English
Subjects:
Algorithmics. Computability. Computer arithmetics
Algorithms
Animals
Applied sciences
Artificial intelligence
Biological and medical sciences
Computer science
control theory
systems
Computer Simulation
Connectionism. Neural networks
Exact sciences and technology
Fundamental and applied biological sciences. Psychology
General aspects. Models. Methods
Humans
Learning - physiology
Learning and adaptive systems
Memory
Models, Neurological
Nerve Net - physiology
Neural Inhibition - physiology
Neural networks
Neural Networks (Computer)
Neurology
Pattern recognition
Periodicity
Punishment
Theoretical computing
Time Factors
Vertebrates: nervous system and sense organs
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a new learning algorithm that leverages oscillations in the strength of neural inhibition to train neural networks. Raising inhibition can be used to identify weak parts of target memories, which are then strengthened. Conversely, lowering inhibition can be used to identify competitors, which are then weakened. To update weights, we apply the Contrastive Hebbian Learning equation to successive time steps of the network. The sign of the weight change equation varies as a function of the phase of the inhibitory oscillation. We show that the learning algorithm can memorize large numbers of correlated input patterns without collapsing and that it shows good generalization to test patterns that do not exactly match studied patterns.
ISSN:0899-7667
1530-888X
DOI:10.1162/neco.2006.18.7.1577