Stochastic weights reinforcement learning for exploratory data analysis

Authors:
Ying Wu;Colin Fyfe;Pei Ling Lai
Affiliations:
Applied Computational Intelligence Research Unit, The University of Paisley, Scotland;Applied Computational Intelligence Research Unit, The University of Paisley, Scotland;Southern Taiwan University of Technology, Tainan, Taiwan
Venue:
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Year:
2007

Citing 9
Cited 1

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Self-organizing maps

Self-organizing maps
GTM: the generative topographic mapping

Neural Computation
Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
A reinforcement learning approach to online clustering

Neural Computation
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Two topographic maps for data visualisation

Data Mining and Knowledge Discovery
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Global Reinforcement Learning in Neural Networks

IEEE Transactions on Neural Networks

2008 Special Issue: Two forms of immediate reward reinforcement learning for exploratory data analysis

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We review a new form of immediate reward reinforcement learning in which the individual unit is deterministic but has stochastic synapses. 4 learning rules have been developed from this perspective and we investigate the use of these learning rules to perform linear projection techniques such as principal component analysis, exploratory projection pursuit and canonical correlation analysis. The method is very general and simply requires a reward function which is specific to the function we require the unit to perform. We also discuss how the method can be used to learn kernel mappings and conclude by illustrating its use on a topology preserving mapping.