The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware

Research output: Contribution to conferencePaper

Standard

The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware. / Trefzer, Martin; Kuyucu, Tueze; Greensted, Andrew; Miller, Julian F.; Tyrrell, Andy M.

2008. 382-391 Paper presented at 8th International Conference on Evolvable Systems, prague, Czech Republic.

Research output: Contribution to conferencePaper

Harvard

Trefzer, M, Kuyucu, T, Greensted, A, Miller, JF & Tyrrell, AM 2008, 'The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware' Paper presented at 8th International Conference on Evolvable Systems, prague, Czech Republic, 1/09/08, pp. 382-391.

APA

Trefzer, M., Kuyucu, T., Greensted, A., Miller, J. F., & Tyrrell, A. M. (2008). The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware. 382-391. Paper presented at 8th International Conference on Evolvable Systems, prague, Czech Republic.

Vancouver

Trefzer M, Kuyucu T, Greensted A, Miller JF, Tyrrell AM. The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware. 2008. Paper presented at 8th International Conference on Evolvable Systems, prague, Czech Republic.

Author

Trefzer, Martin ; Kuyucu, Tueze ; Greensted, Andrew ; Miller, Julian F. ; Tyrrell, Andy M. / The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware. Paper presented at 8th International Conference on Evolvable Systems, prague, Czech Republic.10 p.

Bibtex - Download

@conference{d27935cf6a0a4ed493ef44b18529c9e6,
title = "The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware",
abstract = "Evolution is particularly good at finding specific solutions, which are only valid for exactly the input and environment that are presented during evolution. In most evolution experiments the input pattern order problem is not considered, even though the ability to provide a correct result for any input pattern is a prerequisite for valid circuits. Therefore, the importance of including randomness in the input pattern applied during evolution is addressed in this paper. This is shown to be mandatory-particularly in the case of unconstrained intrinsic evolution of digital circuits-in order to find valid Solutions. The different ways in which unconstrained evolution and constrained evolution exploit resources of a hardware substrate are compared. It is also shown that evolution benefits from versatile input configurations. Furthermore, hierarchical fitness functions. previously introduced to improve the evolution of combinatorial circuits, are applied to the evolution of sequential circuits.",
keywords = "ARCHITECTURE",
author = "Martin Trefzer and Tueze Kuyucu and Andrew Greensted and Miller, {Julian F.} and Tyrrell, {Andy M.}",
year = "2008",
month = "9",
language = "English",
pages = "382--391",
note = "8th International Conference on Evolvable Systems ; Conference date: 01-09-2008",

}

RIS (suitable for import to EndNote) - Download

TY - CONF

T1 - The Input Pattern Order Problem: Evolution of Combinatorial and Sequential Circuits in Hardware

AU - Trefzer, Martin

AU - Kuyucu, Tueze

AU - Greensted, Andrew

AU - Miller, Julian F.

AU - Tyrrell, Andy M.

PY - 2008/9

Y1 - 2008/9

N2 - Evolution is particularly good at finding specific solutions, which are only valid for exactly the input and environment that are presented during evolution. In most evolution experiments the input pattern order problem is not considered, even though the ability to provide a correct result for any input pattern is a prerequisite for valid circuits. Therefore, the importance of including randomness in the input pattern applied during evolution is addressed in this paper. This is shown to be mandatory-particularly in the case of unconstrained intrinsic evolution of digital circuits-in order to find valid Solutions. The different ways in which unconstrained evolution and constrained evolution exploit resources of a hardware substrate are compared. It is also shown that evolution benefits from versatile input configurations. Furthermore, hierarchical fitness functions. previously introduced to improve the evolution of combinatorial circuits, are applied to the evolution of sequential circuits.

AB - Evolution is particularly good at finding specific solutions, which are only valid for exactly the input and environment that are presented during evolution. In most evolution experiments the input pattern order problem is not considered, even though the ability to provide a correct result for any input pattern is a prerequisite for valid circuits. Therefore, the importance of including randomness in the input pattern applied during evolution is addressed in this paper. This is shown to be mandatory-particularly in the case of unconstrained intrinsic evolution of digital circuits-in order to find valid Solutions. The different ways in which unconstrained evolution and constrained evolution exploit resources of a hardware substrate are compared. It is also shown that evolution benefits from versatile input configurations. Furthermore, hierarchical fitness functions. previously introduced to improve the evolution of combinatorial circuits, are applied to the evolution of sequential circuits.

KW - ARCHITECTURE

UR - http://www.scopus.com/inward/record.url?scp=70349876691&partnerID=8YFLogxK

M3 - Paper

SP - 382

EP - 391

ER -