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

Preview

Text
An_information-theoretic_landscape_analysis_of_neuro-controlled_embodied_organisms.pdf
Download (123kB) | Preview

URL: http://dx.doi.org/10.1007/s00521-003-0395-7

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
Keyword:	Artificial life, Artificial neural networks, Embodied cognition, Evolutionary algorithms, Evolutionary robotics, Fitness landscapes
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ1-1570 Mechanical engineering and machinery > TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General) Q Science > QA Mathematics > QA1-939 Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Department:	SCHOOL > School of Engineering and Information Technology
Depositing User:	ADMIN ADMIN
Date Deposited:	20 Oct 2011 09:17
Last Modified:	16 Oct 2017 15:59
URI:	https://eprints.ums.edu.my/id/eprint/923

Actions (login required)

View Item