Skip to main content

Evolving Asynchronous and Scalable Non-uniform Cellular Automata

Sipper, Moshe and Tomassini, Marco and Capcarrere, Mathieu S. (1998) Evolving Asynchronous and Scalable Non-uniform Cellular Automata. In: Artificial Neural Nets and Genetic Algorithms: Proceedings of the International Conference. Springer, Vienna, Austria, pp. 66-69. ISBN 978-3-211-83087-1. E-ISBN 978-3-7091-6492-1. (doi:10.1007/978-3-7091-6492-1_15) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:21651)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1007/978-3-7091-6492-1_15

Abstract

We have previously shown that non-uniform cellular automata (CA) can be evolved to perform computational tasks, using the cellular programming algorithm. In this paper we focus on two novel issues, namely, the evolution of asynchronous CAs, and the scalability of evolved synchronous systems. We find that asynchrony presents a more difficult case for evolution though good CAs can still be attained. We describe an empirically derived scaling procedure by which successful CAs of any size may be obtained from a particular evolved system. Our motivation for this study stems in part from our desire to attain realistic systems that axe more amenable to implementation as “evolving ware,” evolware.

Item Type: Book section
DOI/Identification number: 10.1007/978-3-7091-6492-1_15
Uncontrolled keywords: artificial neural nets ; genetic algorithms ; ICANNGA
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Mark Wheadon
Date Deposited: 22 Aug 2009 14:55 UTC
Last Modified: 16 Feb 2021 12:32 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/21651 (The current URI for this page, for reference purposes)
  • Depositors only (login required):