Combining Hebbian and reinforcement learning in a minibrain model

Authors:
R. J. C. Bosman;W. A. van Leeuwen;B. Wemmenhove
Affiliations:
Institute for Theoretical Physics, University of Amsterdam, Valckenierstraat 65, 1018 XE Amsterdam, The Netherlands;Institute for Theoretical Physics, University of Amsterdam, Valckenierstraat 65, 1018 XE Amsterdam, The Netherlands;Institute for Theoretical Physics, University of Amsterdam, Valckenierstraat 65, 1018 XE Amsterdam, The Netherlands
Venue:
Neural Networks
Year:
2004

Citing 4
Cited 3

Neural networks: an introduction

Neural networks: an introduction
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Reinforcement learning

The handbook of brain theory and neural networks
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning

A Hebbian-based reinforcement learning framework for spike-timing-dependent synapses

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
A novel stochastic learning rule for neural networks

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
A reinforcement learning framework for spiking networks with dynamic synapses

Computational Intelligence and Neuroscience

Quantified Score

Hi-index	0.01

Visualization

Abstract

A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of 'path interference', which makes that the neural net quickly forgets previously learned input-output relations is tackled by adding a Hebbian term (proportional to the learning rate v) to the reinforcement term (proportional to δ) in the learning rule. It is shown that the number of learning steps is reduced considerably if 1/4 v/δ