Using reinforcement learning to guide the development of self-organised feature maps for visual orienting

Authors:
Kevin Brohan;Kevin Gurney;Piotr Dudek
Affiliations:
The University of Manchester, School of Electrical and Electronic Engineering, Manchester, United Kingdom;University of Sheffield, Department of Psychology, Sheffield, United Kingdom;The University of Manchester, School of Electrical and Electronic Engineering, Manchester, United Kingdom
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Year:
2010

Citing 2
Cited 1

The time course of saccadic decision making: dynamic field theory

Neural Networks - 2006 Special issue: Neurobiology of decision making
APRON: a cellular processor array simulation and hardware design tool

EURASIP Journal on Advances in Signal Processing - CNN technology for spatiotemporal signal processing

A real-time, event-driven neuromorphic system for goal-directed attentional selection

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a biologically inspired neural network model of visual orienting (using saccadic eye movements) in which targets are preferentially selected according to their reward value. Internal representations of visual features that guide saccades are developed in a self-organised map whose plasticity is modulated under reward. In this way, only those features relevant for acquiring rewarding targets are generated. As well as guiding the formation of feature representations, rewarding stimuli are stored in a working memory and bias future saccade generation. In addition, a reward prediction error is used to initiate retraining of the self-organised map to generate more efficient representations of the features when necessary.