IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Genetic Programming Using a Turing-Complete Representation: Recurrent Network Consisting of Trees

Genetic Programming Using a Turing-Complete Representation: Recurrent Network Consisting of Trees
View Sample PDF
Author(s): Taro Yabuki (The University of Tokyo, Japan) and Hitoshi Iba (The University of Tokyo, Japan)
Copyright: 2005
Pages: 21
Source title: Recent Developments in Biologically Inspired Computing
Source Author(s)/Editor(s): Leandro Nunes de Castro (Mackenzie University, Brazil) and Fernando J. Von Zuben (State University of Campinas, Brazil)
DOI: 10.4018/978-1-59140-312-8.ch004

Purchase

View Genetic Programming Using a Turing-Complete Representation: Recurrent Network Consisting of Trees on the publisher's website for pricing and purchasing information.

Abstract

In this chapter, a new representation scheme for Genetic Programming (GP) is proposed. We need a Turing-complete representation for a general method of generating programs automatically; that is, the representation must be able to express any algorithms. Our representation is a recurrent network consisting of trees (RTN), which is proved to be Turing-complete. In addition, it is applied to the tasks of generating language classifiers and a bit reverser. As a result, RTN is shown to be usable in evolutionary computing.

Related Content

Mohamed Arezki Mellal. © 2022. 9 pages.
Tahir Cetin Akinci, Ramazan Caglar, Gokhan Erdemir, Aydin Tarik Zengin, Serhat Seker. © 2022. 11 pages.
Sunanda Hazra, Provas Kumar Roy. © 2022. 16 pages.
Ragab A. El-Sehiemy, Almoataz Y. Abdelaziz. © 2022. 23 pages.
Khaled Dassa, Abdelmadjid Recioui. © 2022. 35 pages.
Anupama Kumari, Mukund Madhaw, C. B. Majumder, Amit Arora. © 2022. 21 pages.
Mandrita Mondal. © 2022. 20 pages.
Body Bottom