How inhibitory oscillations can train neural networks and punish competitors

Authors:
Kenneth A. Norman;Ehren Newman;Greg Detre;Sean Polyn
Affiliations:
Department of Psychology, Princeton University, Princeton, NJ;Department of Psychology, Princeton University, Princeton, NJ;Department of Psychology, Princeton University, Princeton, NJ;Department of Psychology, Princeton University, Princeton, NJ
Venue:
Neural Computation
Year:
2006

Citing 7
Cited 2

Deterministic Boltzmann learning performs steepest descent in weight-space

Neural Computation
Learning and relearning in Boltzmann machines

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Setting the activity level in sparse random networks

Neural Computation
Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain

Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain
A proposed function for Hippocampal theta rhythm: separate phases of encoding and retrieval enhance reversal of prior learning

Neural Computation
Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning

Neural Computation

Optimal decision network with distributed representation

Neural Networks
2008 Special Issue: The Emergent neural modeling system

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.