Evolving More Efficient Digital Circuits by Allowing
Circuit Layout Evolution and Multi-Objective Fitness
T. Kalganova, and J. Miller. The First NASA/DoD Workshop on Evolvable Hardware, page 54--63. Pasadena, California, IEEE Computer Society, (19-21 July 1999)
Abstract
We use evolutionary search to design combinational
logic circuits. The technique is based on evolving the
functionality and connectivity of a rectangular array
of logic cells whose dimension is defined by the
circuit layout. The main idea of this approach is to
improve quality of the circuits evolved by the genetic
algorithm (GA) by reducing the number of active gates
used. We accomplish this by combining two ideas: 1)
using multi-objective fitness function; 2) evolving
circuit layout. It will be shown that using these two
approaches allows us to increase the quality of evolved
circuits. The circuits are evolved in two phases.
Initially the genome fitness in given by the percentage
of output bits that are correct. Once 100\% functional
circuits have been evolved, the number of gates
actually used in the circuit is taken into account in
the fitness function. This allows us to evolve circuits
with 100\% functionality and minimise the number of
active gates in circuit structure. The population is
initialised with heterogeneous circuit layouts and the
circuit layout is allowed to vary during the
evolutionary process. Evolving the circuit layout
together with the function is one of the distinctive
features of proposed approach. The experimental results
show that allowing the circuit layout to be flexible is
useful when we want to evolve circuits with the
smallest number of gates used. We find that it is
better to use a fixed circuit layout when the objective
is to achieve the highest number of 100\% functional
circuits. The two-fitness strategy is most effective
when we allow a large number of generations.
%0 Conference Paper
%1 Kalganova:1999:eh
%A Kalganova, T.
%A Miller, J.
%B The First NASA/DoD Workshop on Evolvable Hardware
%C Pasadena, California
%D 1999
%E Stoica, Adrian
%E Lohn, Jason
%E Keymeulen, Didier
%I IEEE Computer Society
%K algorithms, evolvable genetic hardware programming,
%P 54--63
%T Evolving More Efficient Digital Circuits by Allowing
Circuit Layout Evolution and Multi-Objective Fitness
%X We use evolutionary search to design combinational
logic circuits. The technique is based on evolving the
functionality and connectivity of a rectangular array
of logic cells whose dimension is defined by the
circuit layout. The main idea of this approach is to
improve quality of the circuits evolved by the genetic
algorithm (GA) by reducing the number of active gates
used. We accomplish this by combining two ideas: 1)
using multi-objective fitness function; 2) evolving
circuit layout. It will be shown that using these two
approaches allows us to increase the quality of evolved
circuits. The circuits are evolved in two phases.
Initially the genome fitness in given by the percentage
of output bits that are correct. Once 100\% functional
circuits have been evolved, the number of gates
actually used in the circuit is taken into account in
the fitness function. This allows us to evolve circuits
with 100\% functionality and minimise the number of
active gates in circuit structure. The population is
initialised with heterogeneous circuit layouts and the
circuit layout is allowed to vary during the
evolutionary process. Evolving the circuit layout
together with the function is one of the distinctive
features of proposed approach. The experimental results
show that allowing the circuit layout to be flexible is
useful when we want to evolve circuits with the
smallest number of gates used. We find that it is
better to use a fixed circuit layout when the objective
is to achieve the highest number of 100\% functional
circuits. The two-fitness strategy is most effective
when we allow a large number of generations.
%@ 0-7695-0256-3
@inproceedings{Kalganova:1999:eh,
abstract = {We use evolutionary search to design combinational
logic circuits. The technique is based on evolving the
functionality and connectivity of a rectangular array
of logic cells whose dimension is defined by the
circuit layout. The main idea of this approach is to
improve quality of the circuits evolved by the genetic
algorithm (GA) by reducing the number of active gates
used. We accomplish this by combining two ideas: 1)
using multi-objective fitness function; 2) evolving
circuit layout. It will be shown that using these two
approaches allows us to increase the quality of evolved
circuits. The circuits are evolved in two phases.
Initially the genome fitness in given by the percentage
of output bits that are correct. Once 100\% functional
circuits have been evolved, the number of gates
actually used in the circuit is taken into account in
the fitness function. This allows us to evolve circuits
with 100\% functionality and minimise the number of
active gates in circuit structure. The population is
initialised with heterogeneous circuit layouts and the
circuit layout is allowed to vary during the
evolutionary process. Evolving the circuit layout
together with the function is one of the distinctive
features of proposed approach. The experimental results
show that allowing the circuit layout to be flexible is
useful when we want to evolve circuits with the
smallest number of gates used. We find that it is
better to use a fixed circuit layout when the objective
is to achieve the highest number of 100\% functional
circuits. The two-fitness strategy is most effective
when we allow a large number of generations.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Pasadena, California},
author = {Kalganova, T. and Miller, J.},
biburl = {https://www.bibsonomy.org/bibtex/2058afff544fff9e98b997bcf1528ddb5/brazovayeye},
booktitle = {The First NASA/DoD Workshop on Evolvable Hardware},
editor = {Stoica, Adrian and Lohn, Jason and Keymeulen, Didier},
interhash = {ecc9f014163d105ecab1d98e11972a73},
intrahash = {058afff544fff9e98b997bcf1528ddb5},
isbn = {0-7695-0256-3},
keywords = {algorithms, evolvable genetic hardware programming,},
month = {19-21 July},
notes = {EH1999 http://cism.jpl.nasa.gov/events/nasa_eh/},
organisation = {Jet Propulsion Laboratory, California Institute of
Technology},
pages = {54--63},
publisher = {IEEE Computer Society},
publisher_address = {1730 Massachusetts Avenue, N.W., Washington, DC
20036-1992, USA},
timestamp = {2008-06-19T17:42:50.000+0200},
title = {Evolving More Efficient Digital Circuits by Allowing
Circuit Layout Evolution and Multi-Objective Fitness},
year = 1999
}