An information-theoretic landscape analysis of neuro-controlled embodied organisms

Teo, Jason Tze Wi and Abbass, Hussein A. (2004) An information-theoretic landscape analysis of neuro-controlled embodied organisms. Neural Computing & Applications, 13 (1). pp. 80-89. ISSN 0941-0643

[img]
Preview
Text
An_information-theoretic_landscape_analysis_of_neuro-controlled_embodied_organisms.pdf

Download (123kB) | Preview

Abstract

Recently, there has been a lot of interest in evolving controllers for both physically simulated creatures as well as for real physical robots. However, a range of different ANN architectures are used for controller evolution, and, in the majority of the work conducted, the choice of the architecture used is made arbitrarily. No fitness landscape analysis was provided for the underlying fitness landscape of the controller's search space. As such, the literature remains largely inconclusive as to which ANN architecture provides the most efficient and effective space for searching the range of possible controllers through evolutionary methods. This represents the motivation for this paper where we compare the search space for four different types of ANN architecture for controller evolution through an information-theoretic analysis of the fitness landscape associated with each type of architecture.

Item Type: Article
Uncontrolled Keywords: Artificial life, Artificial neural networks, Embodied cognition, Evolutionary algorithms, Evolutionary robotics, Fitness landscapes
Subjects: ?? TJ210.2-211.47 ??
?? QA75.5-76.95 ??
Divisions: SCHOOL > School of Engineering and Information Technology
Depositing User: Unnamed user with email storage.bpmlib@ums.edu.my
Date Deposited: 20 Oct 2011 01:17
Last Modified: 16 Oct 2017 07:59
URI: http://eprints.ums.edu.my/id/eprint/923

Actions (login required)

View Item View Item