Important note: Do NOT send email to the cs.cf.ac.uk address above: it will
be ignored. Corrections and other correspondence should be sent to
TABLE OF CONTENTS OF PART 5
Q20: What EA software packages are available?
Q20.1: Free software packages?
Q20.2: Commercial software packages?
Q20.3: Current research projects?
Subject: Q20: What EA software packages are available?
This gives a list of all known EA software packages available to the
public. The list was originally maintained by Nici Schraudolph. In
June '93 it was agreed that it would be incorporated into this FAQ
and the responsibility for maintenance taken over by the FAQ editor.
A copy of most of the packages described below are kept at ENCORE,
(See Q15.3), available by anonymous FTP.
Most GENETIC PROGRAMMING software is available by FTP in:
ftp.io.com/pub/genetic-programming/ There are subdirectories
containing papers related to GP, archives of the mailing list, as
well as a suite of programs for implementing GP. These programs
include the Lisp code from Koza's "Genetic Programming" [KOZA92], as
well as implementations in C and C++, as for example SGPC: Simple
Genetic Programming in C by Walter Alden Tackett and Aviram Carmi
A survey paper entitled "Genetic Algorithm Programming Environments"
was published in IEEE Computer in the June 1994 issue. Written by
Filho, Alippi and Treleaven of University College, London, UK. It's
available by FTP as bells.cs.ucl.ac.uk/papagena/game/docs/gasurvey.ps
(file size: 421k).
For many of these software packages, specific ordering instructions
are given in the descriptions below (see Q20.1 - Free Software
packages, Q20.2 - Commercial Software Packages, Q20.3 - Research
Projects). Please read and follow them before unnecessarily
bothering the listed author or contact! Also note that these
programs haven't been independently tested, so there are no
guarantees of their quality.
A major revision was undertaken in August 1994, when all authors were
contacted, and asked to confirm the accuracy of the information
contained here. A few authors did not respond to the request for
information. These are noted below by: (Unverified 8/94). In these
cases, FTP address were checked by the FAQ editor, to confirm that
this information (at least) is correct. In two cases, email to the
author bounced back as "undeliverable" -- these are noted below.
Type (this is a very ad-hoc classification)
GE: generational GA
SS: steady-state GA
PA: (pseudo) parallel GA
ES: evolution strategy
XP: expert system
CF: classifier system
OS Operating System; X11 implies Unix; "Win" means Microsoft
Windows 3.x/NT (PC); "DOS" means MS-DOS or compatibles.
Lang Programming Language; in parentheses: source code not included;
"OPas" = MPW Object Pascal
Price (circa 1994)
(1) free to government contractors, $221 otherwise, (2)
educational discount available, (3) available as addendum to a
book, (4) single 1850 DM, site license 5200 DM, (5) single 200
DM, site license 500 DM, (6) free for academic and educational
Author or Contact
Name of creator/maintainer. For internet e-mail addresses, refer
to the details of the specific package.
ES/GA/XP System Implementations:
Name Type OS Lang Price Author/Contact
BUGS GE, X11, C free Joshua Smith
Computer- ED, Win ? free Scott Kennedy
DGenesis GE, Unix C free Erick Cantu-Paz
DOUGAL SS, DOS Turbo free Brett Parker
Ease GE, Unix Tcl free Joachim Sprave
ESCaPaDE ES Unix C free Frank Hoffmeister
Evolution GE, DOS C free Hans-Michael Voigt and
Machine ES Joachim Born
Evolutionary GE, Unix C++ free JJ Merelo
GAC, GE Unix C free Bill Spears
GAL " " Lisp "
GAGA GE Unix C free Jon Crowcroft
GAGS GE, Unix, C++ free JJ Merelo
GAlib GA Unix, C++ free Matthew Wall
GALOPPS GE, Unix, C free Erik Goodman
GAMusic ED Win (VB) $10 Jason H. Moore
GANNET GE, Unix C free Darrell Duane
GAucsd GE Unix C free Nici Schraudolph
GA GE, DOS (C++) free Mark Hughes
GECO GE, Unix, Lisp free George P. W. Williams, Jr.
Genesis GE, Unix, C free John Grefenstette
GENEsYs GE Unix C free Thomas Baeck
GenET SS, Unix, C free Cezary Z. Janikow
ES,ED X, etc.
Genie GE Mac Think free Lance Chambers
Genitor SS Unix C free Darrell Whitley
GENlib SS Unix, C (6) Jochen Ruhland
GENOCOP GE Unix C free Zbigniew Michalewicz
GIGA SS Unix C free Joe Culberson
GPEIST GP Win, Small- free Tony White
Imogene GP Win C++ free Harley Davis
JAG GA - Java free Stephen Hartley
LibGA GE, Unix/DOS C free Art Corcoran
LICE ES Unix, C free Joachim Sprave
Matlab-GA GE ? Matlab free Andy Potvin
mGA GE Unix C, free Dave Goldberg
PARAGenesis PA, CM C* free Michael van Lent
PGA PA, Unix, C free Peter Ross
PGAPack GA, any C free David Levine
REGAL GA C free Filippo Neri
SGA-C, GE Unix C free Robert E. Smith
Splicer GE Mac, C (1) Steve Bayer
TOLKIEN OO, Unix, C++ free Anthony Yiu-Cheung Tang
Learning NN Win ? free Universal Problem Solvers
WOLF SS Unix C free David Rogers
XGenetic GA, Win ActiveX free Jeff Goslin
Classifier System Implementations:
Name Type OS Lang Price Author/Contact
CFS-C CF, Unix/DOS C free Rick Riolo
SCS-C CF, Unix/DOS C free Joerg Heitkoetter
ED Atari TOS
Name Type OS Lang Price Author/Contact
ActiveGA GA Win (ActiveX) $99 Brightwater Software
EnGENEer OO, X11 C ? George Robbins,
GA Logica Cambridge Ltd.
EvoFrame/ OO, Mac, C++/ (4,2) Optimum Software
REALizer ES DOS OPas (5,2)
Evolver GE DOS, (C, UKP350 Palisade
FlexTool GA Win Matlab ? Flexible Intelligence Group
GAME OO, X11 C++ (3) Jose R. Filho
GeneHunter GA Win, (VB) $369 Ward Systems
Generator GE,SS Win, (C++) $379 Steve McGrew, New Light Industries
Genetic GE,SS Win (ActiveX) ? NeuroDimension Inc.
MicroGA/ OO, Mac, C++ $249 Emergent Behavior, Inc.
Galapagos SS Win (2)
Omega ? DOS ? ? David Barrow, KiQ Ltd.
OOGA OO, Mac, Lisp $60 Lawrence Davis
optiGA ? Win VB, ? Elad Salomons
PC/Beagle XP DOS ? 69UKP Richard Forsyth
XpertRule/ XP DOS (Think 995UKP Attar Software
XYpe SS Mac (C) $725 Ed Swartz, Virtual Image Inc.
Subject: Q20.1: Free software packages?
BUGS (Better to Use Genetic Systems) is an interactive program for
demonstrating the GENETIC ALGORITHM and is written in the spirit of
Richard Dawkins' celebrated Blind Watchmaker software. The user can
play god (or `GA FITNESS function,' more accurately) and try to
evolve lifelike organisms (curves). Playing with BUGS is an easy way
to get an understanding of how and why the GA works. In addition to
demonstrating the basic GENETIC OPERATORs (SELECTION, CROSSOVER, and
MUTATION), it allows users to easily see and understand phenomena
such as GENETIC DRIFT and premature convergence. BUGS is written in C
and runs under Suntools and X Windows.
BUGS was written by Joshua Smith <email@example.com> at Williams
College and is available from
www.aic.nrl.navy.mil/pub/galist/src/BUGS.tar.Z Note that it is
unsupported software, copyrighted but freely distributable. Address:
Room E15-492, MIT Media Lab, 20 Ames Street, Cambridge, MA 02139.
ComputerAnts is a free Windows program that teaches principles of
GENETIC ALGORITHMs by breeding a colony of ants on your computer
screen. Users create ants, food, poison, and set CROSSOVER and
MUTATION rates. Then they watch the colony slowly evolve. Includes
extensive on-line help and tutorials on genetic algorithms. For
further information or to download, see the download section under
DGenesis is a distributed implementation of a Parallel GA. It is
based on Genesis 5.0. It runs on a network of UNIX workstations. It
has been tested with DECstations, microVAXes, Sun Workstations and
PCs running 386BSD 0.1. Each subpopulation is handled by a UNIX
process and the communication between them is accomplished using
Berkeley sockets. The system is programmed in C and is available free
of charge by anonymous FTP from ftp://lamport.rhon.itam.mx/ and from
DGenesis allows the user to set the MIGRATION interval, the migration
rate and the topology between the SUB-POPULATIONs. There has not
been much work investigating the effect of the topology on the
PERFORMANCE of the GA, DGenesis was written specifically to encourage
experimentation in this area. It still needs many refinements, but
some may find it useful.
Contact Erick Cantu-Paz <firstname.lastname@example.org> at the
Instituto Tecnologico Autonomo de Mexico (ITAM)
DOUGAL is a demonstration program for solving the TRAVELLING SALESMAN
PROBLEM using GAs. The system guides the user through the GA,
allowing them to see the results of altering parameters relating to
CROSSOVER, MUTATION etc. The system demonstrates graphicaly the
OPTIMIZATION of the route. The options open to the user to
experiment with include percentage CROSSOVER and MUTATION, POPULATION
size, steady state or generational replacement, FITNESS technique
(linear normalised, is evaluation, etc).
DOUGAL requires an IBM compatible PC with a VGA monitor. The
software is free, however I would appreciate feedback on what you
think of the software.
Dougal is available by FTP from ENCORE (see Q15.3) in file
EC/GA/src/dougal.zip It's pkzipped and contains executable, vga
driver, source code and full documentation. It is important to place
the vga driver (egavga.bgi) in the same directory as DOUGAL. Author:
Brett Parker, 7 Glencourse, East Boldon, Tyne + Wear, NE36 0LW,
Ease - Evolutionary Algorithms Scripting Environment - is an
extension to the Tcl scripting language, providing commands to
create, modify, and evaluate POPULATIONs of INDIVIDUALs represented
by real number vectors and/or bit strings. With Ease, a standard ES
or GA can be written in less than 20 lines of code.
Ease is available as source code for Linux and Solaris under the GNU
Public License. Tcl version 8.0 or higher is required. If you know
how generate DLLs, you may be able to use it on Win9x/NT, as well.
The URL is http://www.sprave.com/Ease/Ease.html . Written by Joachim
ESCaPaDE is a sophisticated software environment to run experiments
with EVOLUTIONARY ALGORITHMs, such as e.g. an EVOLUTION STRATEGY.
The main support for experimental work is provided by two internal
tables: (1) a table of objective functions and (2) a table of so-
called data monitors, which allow easy implementation of functions
for monitoring all types of information inside the Evolutionary
Algorithm under experiment.
ESCaPaDE 1.2 comes with the KORR implementation of the evolution
strategy by H.-P. Schwefel which offers simple and correlated
MUTATIONs. KORR is provided as a FORTRAN 77 subroutine, and its
cross-compiled C version is used internally by ESCaPaDE.
An extended version of the package was used for several
investigations so far and has proven to be very reliable. The
software and its documentation is fully copyrighted although it may
be freely used for scientific work; it requires 5-6 MB of disk space.
In order to obtain ESCaPaDE, please send a message to the e-mail
address below. The SUBJECT line should contain 'help' or 'get
ESCaPaDE'. (If the subject lines is invalid, your mail will be
ignored!). For more information contact: Frank Hoffmeister, Systems
Analysis Research Group, LSXI, Department of Computer Science,
University of Dortmund, D-44221 Dortmund, Germany. Net:
The Evolution Machine (EM) is universally applicable to continuous
(real-coded) OPTIMIZATION problems. In the EM we have coded
fundamental EVOLUTIONARY ALGORITHMs (GENETIC ALGORITHMs and EVOLUTION
STRATEGIEs), and added some of our approaches to evolutionary search.
The EM includes extensive menu techniques with:
o Default parameter setting for unexperienced users.
o Well-defined entries for EM-control by freaks of the EM, who
want to leave the standard process control.
o Data processing for repeated runs (with or without change of the
o Graphical presentation of results: online presentation of the
EVOLUTION progress, one-, two- and three-dimensional graphic
output to analyse the FITNESS function and the evolution process.
o Integration of calling MS-DOS utilities (Turbo C).
We provide the EM-software in object code, which can be run on PC's
with MS-DOS and Turbo C, v2.0, resp. Turbo C++,v1.01. The Manual to
the EM is included in the distribution kit.
The EM software is available by FTP from ftp-bionik.fb10.tu-
berlin.de/pub/software/Evolution-Machine/ This directory contains the
compressed files em_tc.exe (Turbo C), em_tcp.exe (Turbo C++) and
em_man.exe (the manual). There is also em-man.ps.Z, a compressed
PostScript file of the manual. If you do not have FTP access, please
send us either 5 1/4 or 3 1/2 MS-DOS compatible disks. We will return
them with the compressed files (834 kB).
Official contact information: Hans-Michael Voigt or Joachim Born,
Technical University Berlin, Bionics and evolution Techniques
Laboratory, Bio- and Neuroinformatics Research Group, Ackerstrasse
71-76 (ACK1), D-13355 Berlin, Germany. Net: <email@example.com-
berlin.de>, <firstname.lastname@example.org> (Unverified 8/94).
EO (Evolutionary Objects) is a C++ library written and designed to
allow a variety of evolutionary algorithms to be constructed easily.
It is intended to be an "Open source" effort to create the definitive
EC library. It has: a mailing list, anon-CVS access, frequent
snapshots and other features. For details, see http://fast.to/EO
Maintained by J.J. Merelo, Grupo Geneura, Univ. Granada <jmerelo@kal-
A mouse-driven interactive GA demonstration program aimed at people
wishing to show GAs in action on simple FUNCTION OPTIMIZATIONs and to
help newcomers understand how GAs operate. Features: problem
functions drawn on screen using mouse, run-time plots of GA
POPULATION distribution, peak and average FITNESS. Useful population
STATISTICS displayed numerically, GA configuration (population size,
GENERATION gap etc.) performed interactively with mouse.
Requirements: MS-DOS PC, mouse, EGA/VGA display.
Available by FTP from the simtel20 archive mirrors, e.g. wsmr-
wuarchive.wustl.edu: or oak.oakland.edu: Produced by Mark Hughes
<email@example.com>. A windows version is in preparation.
Bill Spears <firstname.lastname@example.org> writes: These are packages I've
been using for a few years. GAC is a GA written in C. GAL is my
Common Lisp version. They are similar in spirit to John
Grefenstette's Genesis, but they don't have all the nice bells and
whistles. Both versions currently run on Sun workstations. If you
have something else, you might need to do a little modification.
Both versions are free: All I ask is that I be credited when it is
appropriate. Also, I would appreciate hearing about improvements!
This software is the property of the US Department of the Navy.
The code will be in a "shar" format that will be easy to install.
This code is "as is", however. There is a README and some
documentation in the code. There is NO user's guide, though (nor am I
planning on writing one at this time). I am interested in hearing
about bugs, but I may not get around to fixing them for a while.
Also, I will be unable to answer many questions about the code, or
about GAs in general. This is not due to a lack of interest, but due
to a lack of free time!
Available by FTP from
ftp.aic.nrl.navy.mil/pub/galist/src/ga/GAC.shar.Z and GAL.shar.Z .
PostScript versions of some papers are under "/pub/spears". Feel
free to browse.
GAGA (GA for General Application) is a self-contained, re-entrant
procedure which is suitable for the minimization of many "difficult"
cost functions. Originally written in Pascal by Ian Poole, it was
rewritten in C by Jon Crowcroft. GAGA can be obtained by request from
the author: Jon Crowcroft <email@example.com>, Univeristy College
London, Gower Street, London WCIE 6BT, UK, or by FTP from
GAGS (Genetic Algorithms from Granada, Spain) is a library and
companion programs written and designed to take the heat out of
designing a GENETIC ALGORITHM. It features a class library for
genetic algorithm programming, but, from the user point of view, is a
genetic algorithm application generator. Just write the function you
want to optimize, and GAGS surrounds it with enough code to have a
genetic algorithm up and running, compiles it, and runs it. GAGS Is
written in C++, so that it can be compiled in any platform running
this GNU utility. It has been tested on various machines.
Documentation is available.
o Steady-state, roulette-wheel, tournament and elitist SELECTION.
o FITNESS evaluation using training files.
o Graphics output through gnuplot.
o Uniform and 2-point CROSSOVER, and bit-flip and gene-transposition
o Variable length CHROMOSOMEs and related operators.
The application generator gags.pl is written in perl, so this
language must also be installed before GAGS. Available from:
http://kal-el.ugr.es/GAGS The programmer's manual is in the file
gagsprogs.ps.gz. GAGS is also available from ENCORE (see Q15.3) in
file EC/GA/src/gags-0.92.tar.gz (there may be a more recent version)
with documentation in EC/GA/docs/gagsprog.ps.gz
Maintained by J.J. Merelo, Grupo Geneura, Univ. Granada <jmerelo@kal-
GAlib is a C++ library that provides the application programmer with
a set of GENETIC ALGORITHM objects. With GAlib you can add GA
OPTIMIZATION to your program using any data representation and
standard or custom SELECTION, CROSSOVER, MUTATION, scaling, and
replacement, and termination methods. View the documentation on-line
at http://lancet.mit.edu/ga/ There you will find a complete
description of the programming interface, features, and examples.
The canonical source for this library is the FTP site:
lancet.mit.edu/pub/ga/ This directory contains UNIX (.tar.gz), MacOS
(.sea.hqx), and DOS (.zip) versions of the GA library. Once you have
downloaded the file, uncompress and extract it. It will expand to
its own directory. If you extract the DOS version be sure to use the
-d option to keep everything in one directory.
GAlib requires a cfront 3.0 compatible C++ compiler. It has been
used on the following systems: SGI IRIX 4.0.x (Cfront); SGI IRIX 5.x
(DCC 1.0, g++ 2.6.8, 2.7.0); IBM RSAIX 3.2 (g++ 2.6.8, 2.7.0); DEC
MIPS ultrix 4.2 (g++ 2.6.8, 2.7.0); SUN SOLARIS 5.3 (g++ 2.6.8,
2.7.0); HP-UX (g++); MacOS (MetroWerks CodeWarrior 5); MacOS
(Symantec THINK C++ 7.0); DOS/Windows (Borland Turbo C++ 3.0).
Maintained by: Matthew Wall <firstname.lastname@example.org>
GALOPPS (Genetic Algorithm Optimized for Portability and Parallelism)
is a general-purpose parallel GENETIC ALGORITHM system, written in
'C', organized like Goldberg's "Simple Genetic Algorithm". User
defines objective function (in template furnished) and any callback
functions desired (again, filling in template); can run one or many
subpopulations, on one or many PC's, workstations, Mac's, MPP. Runs
interactively (GUI or answering questions) or from files, makes file
and/or graphical output. Runs easily interrupted and restarted, and
a PVM version for Unix networks even moves processes automatically
when workstations become busy. (Note: optional GUI requires Tcl/Tk.)
14 example problems included (De Jong Functions, Royal Road, BTSP,
User may choose:
o problem type (permutation or value-type)
o field sizes (arbitrary, possibly unequal, heeded by CROSSOVER,
o among 7 crossover types and 4 mutation types (or define own)
o among 6 SELECTION types, including "automatic" option based on
Boltzmann scaling and Shapiro and Pruegel-Bennett statist.
o operator probabilities, FITNESS scaling, amount of output,
MIGRATION frequency and patterns,
o stopping criteria (using "standard" convergence STATISTICS, etc.)
o the GGA (Grouping Genetic Algorithm) REPRODUCTION and operators of
GALOPPS allows and supports:
o use of a different representation in each subpopulation, with
transformation of migrants
o INVERSION on level of subpopulations, with automatic handling of
differing field sizes, migrants
o control over replacement by OFFSPRING, including DeJong crowding
or random replacement or SGA-like replacement of PARENTs
o mate selection, using incest reduction
o migrant selection, using incest reduction, and/or DeJong crowding
into receiving subpopulation
o optional ELITISM
Generic (Unix) GALOPPS 3.2 (includes 80-pp. manual) is available on
ENCORE. For PVM GALOPPS, PC version (different line endings,
makefiles), Threaded GALOPPS, and GALOPPS-based 2-level adaptive
system, see the MSU GARAGe web site: http://GARAGe.cps.msu.edu/ .
Contact: Erik D. Goodman, <email@example.com>, MSU GARAGe, Case
Center, 112 Engineering Building, MSU, East Lansing, MI 48824 USA.
GAMusic 1.0 is a user-friendly interactive demonstration of a simple
GA that evolves musical melodies. Here, the user is the FITNESS
function. Melodies from the POPULATION can be played and then
assigned a fitness. Iteration, RECOMBINATION frequency and MUTATION
frequency are all controlled by the user. This program is intended
to provide an introduction to GAs and may not be of interest to the
experienced GA programmer.
GAMusic was programmed with Microsoft Visual Basic 3.0 for Windows
3.1x. No special sound card is required. GAMusic is distributed as
shareware (cost $10) and can be obtained by FTP from
wuarchive.wustl.edu/pub/MSDOS_UPLOADS/GenAlgs/gamusic.zip or from
fly.bio.indiana.edu/science/ibmpc/gamusic.zip The program is also
available from the America Online archive.
Contact: Jason H. Moore <firstname.lastname@example.org> or
GANNET (Genetic Algorithm / Neural NETwork) is a software package
written by Jason Spofford in 1990 which allows one to evolve binary
valued neural networks. It offers a variety of configuration options
related to rates of the GENETIC OPERATORs. GANNET evolves nets based
upon three FITNESS functions: Input/Output Accuracy, Output
'Stability', and Network Size.
The evolved neural network presently has a binary input and binary
output format, with neurodes that have either 2 or 4 inputs and
weights ranging from -3 to +4. GANNET allows for up to 250 neurons
in a net. Research using GANNET is continuing.
GANNET 2.0 is available at http://www.duane.com/~dduane/gannet
. As well as the software, the masters thesis that utilized this
program as well as a paper is available in this directory.
The major enhancement of version 2.0 is the ability to recognize
variable length binary strings, such as those that would be generated
by a finite automaton. Included is code for calculating the
Effective Measure Complexity (EMC) of finite automata as well as code
for generating test data.
A mailing list has been established for discussing uses and problems
with the GANNET software. To subscribe, send a message to:
<email@example.com> On the first line of the message (not the
subject) type: subscribe gannet
Contact: Darrell Duane <firstname.lastname@example.org> or Dr. Kenneth Hintz
<email@example.com>, George Mason University, Dept. of Electrical &
Computer Engineering, Mail Stop 1G5, 4400 University Drive, Fairfax,
VA 22033-4444 USA.
GAucsd is a Genesis-based GA package incorporating numerous bug fixes
and user interface improvements. Major additions include a wrapper
that simplifies the writing of evaluation functions, a facility to
distribute experiments over networks of machines, and Dynamic
Parameter Encoding, a technique that improves GA PERFORMANCE in
continuous SEARCH SPACEs by adaptively refining the genomic
representation of real-valued parameters.
GAucsd was written in C for Unix systems, but the central GA engine
is easily ported to other platforms. The entire package can be ported
to systems where implementations of the Unix utilities "make", "awk"
and "sh" are available.
GAucsd is available by FTP from
ftp.cs.ucsd.edu/pub/GAucsd/GAucsd14.sh.Z or from
ftp.aic.nrl.navy.mil/pub/galist/src/GAucsd14.sh.Z To be added to a
mailing list for bug reports, patches and updates, send "add GAucsd"
Cognitive Computer Science Research Group, CSE Department, UCSD 0114,
La Jolla, CA 92093-0114, USA. Net: <GAucsdfirstname.lastname@example.org>
GECO (Genetic Evolution through Combination of Objects) is an
extensible, object-oriented framework for prototyping GENETIC
ALGORITHMs in Common Lisp. GECO makes extensive use of CLOS, the
Common Lisp Object System, to implement its functionality. The
abstractions provided by the classes have been chosen with the intent
both of being easily understandable to anyone familiar with the
paradigm of genetic algorithms, and of providing the algorithm
developer with the ability to customize all aspects of its operation.
It comes with extensive documentation, in the form of a PostScript
file, and some simple examples are also provided to illustrate its
GECO Version 2.0 is available by FTP. See the file
ftp.aic.nrl.navy.mil/pub/galist/src/ga/GECO-v2.0.README for more
George P. W. Williams, Jr., 1334 Columbus City Rd., Scottsboro, AL
35768. Net: <email@example.com>.
Genesis is a generational GA system written in C by John Grefenstette
<firstname.lastname@example.org>. As the first widely available GA program
Genesis has been very influential in stimulating the use of GAs, and
several other GA packages are based on it. Genesis is available
together with OOGA (see below), or by FTP from
ftp.aic.nrl.navy.mil/pub/galist/src/genesis.tar.Z (Unverified 8/94).
GENEsYs is a Genesis-based GA implementation which includes
extensions and new features for experimental purposes, such as
SELECTION schemes like linear ranking, Boltzmann, (mu,
lambda)-selection, and general extinctive selection variants,
CROSSOVER operators like n-point and uniform crossover as well as
discrete and intermediate RECOMBINATION. SELF-ADAPTATION of MUTATION
rates is also possible.
A set of objective functions is provided, including De Jong's
functions, complicated continuous functions, a TSP-problem, binary
functions, and a fractal function. There are also additional data-
monitoring facilities such as recording average, variance and skew of
OBJECT VARIABLES and mutation rates, or creating bitmap-dumps of the
GENEsYs 1.0 is available via FTP from lumpi.informatik.uni-
dortmund.de/pub/GA/src/GENEsYs-1.0.tar.Z The documentation alone is
available as /pub/GA/docs/GENEsYs-1.0-doc.tar.Z
For more information contact: Thomas Baeck, Systems Analysis Research
Group, LSXI, Department of Computer Science, University of Dortmund,
D-44221 Dortmund, Germany. Net: <email@example.com-
dortmund.de> (Unverified 8/94).
GenET is a "generic" GA package. It is generic in the sense that all
problem independent mechanisms have been implemented and can be used
regardless of application domain. Using the package forces (or
allows, however you look at it) concentration on the problem: you
have to suggest the best representation, and the best operators for
such space that utilize your problem-specific knowledge. You do not
have to think about possible GA models or their implementation.
The package, in addition to allowing for fast implementation of
applications and being a natural tool for comparing different models
and strategies, is intended to become a depository of representations
and operators. Currently, only floating point representation is
implemented in the library with few operators.
The algorithm provides a wide selection of models and choices. For
example, POPULATION models range from generational GA, through
steady-state, to (n,m)-EP and (n,n+m)-EP models (for arbitrary
problems, not just parameter OPTIMIZATION). (Some are not finished
at the moment). Choices include automatic adaptation of operator
probabilities and a dynamic ranking mechanism, etc.
Even though the implementation is far from optimal, it is quite
efficient - implemented in ATT's C++ (3.0) (functional design) and
also tested on gcc. Along with the package you will get two
examples. They illustrate how to implement problems with
heterogeneous and homogeneous structures, with explicit rep/opers and
how to use the existing library (FP). Very soon I will place there
another example - our GENOCOP operators for linearly constrained
optimization. One more example soon to appear illustrates how to
deal with complex structures and non-stationary problems - this is a
fuzzy rule-based controller optimized using the package and some
If you start using the package, please send evaluations (especially
bugs) and suggestions for future versions to the author.
GenET Version 1.00 is available by FTP from
radom.umsl.edu/var/ftp/GenET.tar.Z To learn more, you may get the
User's Manual, available in compressed postscript in
"/var/ftp/userMan.ps.Z". It also comes bundled with the complete
Cezary Z. Janikow, Department of Math and CS, CCB319, St. Louis, MO
63121, USA. Net: <firstname.lastname@example.org>
Genie is a GA-based modeling/forecasting system that is used for
long-term planning. One can construct a model of an ENVIRONMENT and
then view the forecasts of how that environment will evolve into the
future. It is then possible to alter the future picture of the
environment so as to construct a picture of a desired future (I will
not enter into arguments of who is or should be responsible for
designing a desired or better future). The GA is then employed to
suggest changes to the existing environment so as to cause the
desired future to come about.
Genie is available free of charge via e-mail or on 3.5'' disk from:
Lance Chambers, Department of Transport, 136 Stirling Hwy, Nedlands,
West Australia 6007. Net: <email@example.com> It is also
available by FTP from hiplab.newcastle.edu.au/pub/Genie&Code.sea.Hqx
"Genitor is a modular GA package containing examples for floating-
point, integer, and binary representations. Its features include many
sequencing operators as well as subpopulation modeling.
The Genitor Package has code for several order based CROSSOVER
operators, as well as example code for doing some small TSPs to
We are planning to release a new and improved Genitor Package this
summer (1993), but it will mainly be additions to the current package
that will include parallel island models, cellular GAs, delta coding,
perhaps CHC (depending on the legal issues) and some other things we
have found useful."
Genitor is available from Colorado State University Computer Science
Department by FTP from ftp.cs.colostate.edu/pub/GENITOR.tar
Please direct all comments and questions to
<firstname.lastname@example.org>. If these fail to work, contact: L.
Darrell Whitley, Dept. of Computer Science, Colorado State
University, Fort Collins, CO 80523, USA. Net:
<email@example.com> (Unverified 8/94).
GENlib is a library of functions for GENETIC ALGORITHMs. Included
are two applications of this library to the field of neural networks.
The first one called "cosine" uses a genetic algorithm to train a
simple three layer feed-Forward network to work as a cosine-function.
This task is very difficult to train for a backprop algorithm while
the genetic algorithm produces good results. The second one called
"vartop" is developing a Neural Network to perform the XOR-function.
This is done with two genetic algorithms, the first one develops the
topology of the network, the second one adjusts the weights.
GENlib may be obtained by FTP from ftp.neuro.informatik.uni-
Author: Jochen Ruhland, FG Neuronale Netzwerke / Uni Kassel,
Heinrich-Plett-Str. 40, D-34132 Kassel, Germany.
This is a GA-based OPTIMIZATION package that has been developed by
Zbigniew Michalewicz and is described in detail in his book Genetic
Algorithms + Data Structures = Evolution Programs [MICHALE94].
GENOCOP (Genetic Algorithm for Numerical Optimization for COnstrained
Problems) optimizes a function with any number of linear constraints
(equalities and inequalities).
The second version of the system is available by FTP from
Zbigniew Michalewicz, Dept. of Computer Science, University of North
Carolina, Chappel-Hill, NC, USA. Net: <firstname.lastname@example.org>
GIGA is designed to propogate information through a POPULATION, using
CROSSOVER as its operator. A discussion of how it propogates BUILDING
BLOCKs, similar to those found in Royal Road functions by John
Holland, is given in the DECEPTION section of: "Genetic Invariance: A
New Paradigm for Genetic Algorithm Design." University of Alberta
Technical Report TR92-02, June 1992. See also: "GIGA Program
Description and Operation" University of Alberta Computing Science
Technical Report TR92-06, June 1992
These can be obtained, along with the program, by FTP from
ftp.cs.ualberta.ca/pub/TechReports/ in the subdirectories TR92-02/
and TR92-06/ .
Also, the paper "Mutation-Crossover Isomorphisms and the Construction
of Discriminating Functions" gives a more in-depth look at the
behavior of GIGA. Its is available from
Joe Culberson, Department of Computer Science, University of Alberta,
CA. Net: <email@example.com>
The GENETIC PROGRAMMING ENVIRONMENT in Smalltalk (GPEIST) provides a
framework for the investigation of Genetic Programming within a
ParcPlace VisualWorks 2.0 development system. GPEIST provides
program, POPULATION, chart and report browsers and can be run on
HP/Sun/PC (OS/2 and Windows) machines. It is possible to distribute
the experiment across several workstations - with subpopulation
exchange at intervals - in this release 4.0a. Experiments,
populations and INDIVIDUAL genetic programs can be saved to disk for
subsequent analysis and experimental statistical measures exchanged
with spreadsheets. Postscript printing of charts, programs and
animations is supported. An implementation of the Ant Trail problem
is provided as an example of the use of the GPEIST environment.
GPEIST is available from ENCORE (see Q15.3) in file:
Contact: Tony White, Bell-Northern Research Ltd., Computer Research
Lab - Gateway, 320 March Road, Suite 400, Kanata, Ontario, Canada,
K2K 2E3. tel: (613) 765-4279 <firstname.lastname@example.org>
Imogene is a Windows 3.1 shareware program which generates pretty
images using GENETIC PROGRAMMING. The program displays GENERATIONs
of 9 images, each generated using a formula applied to each pixel.
(The formulae are initially randomly computed). You can then select
those images you prefer. In the next generation, the nine images are
generated by combining and mutating the formulae for the most-
preferred images in the previous generation. The result is a
SIMULATION of natural SELECTION in which images evolve toward your
Imogene supports different color maps, palette animation, saving
images to .BMP files, changing the wallpaper to nice images, printing
images, and several other features. Imogene works only in 256 color
mode and requires a floating point coprocessor and a 386 or better
Imogene is based on work originally done by Karl Sims at
(ex-)Thinking Machines for the CM-2 massively parallel computer - but
you can use it on your PC. You can get Imogene from:
Contact: Harley Davis, ILOG S.A., 2 Avenue Gallini, BP 85, 94253
Gentilly Cedex, France. tel: +33 1 46 63 66 66 <email@example.com>
This Java program implements a simple GENETIC ALGORITHM where the
FITNESS function takes non-negative values only. It employs ELITISM.
The Java code was derived from the C code in the Appendix of Genetic
Algorithms + Data Structures = Evolution Programs, [MICHALE94].
Other ideas and code were drawn from GAC by Bill Spears.
Four sample problems are contained in the code: three with bit GENEs
and one with double genes. To use this program, modify the class
MyChromosome to include your problem, which you have coded in some
class, say YourChromosome. All changes to the sGA.java file to run
your problem are confined to your class YourChromosome. This is what
object-oriented programming is all about! The sGA.java source code
file has a big comment at the end containing some sample runs.
Available by FTP from ftp.mcs.drexel.edu/pub/shartley/simpleGA.tar.gz
. Further information from Stephen J. Hartley
<firstname.lastname@example.org>, http://www.mcs.drexel.edu/~shartley .
Drexel University, Math and Computer Science Department Philadelphia,
PA 19104 USA. +1-215-895-2678
LibGA is a library of routines written in C for developing GENETIC
ALGORITHMs. It is fairly simple to use, with many knobs to turn.
Most GA parameters can be set or changed via a configuration file,
with no need to recompile. (E.g., operators, pool size and even the
data type used in the CHROMOSOME can be changed in the configuration
file.) Function pointers are used for the GENETIC OPERATORs, so they
can easily be manipulated on the fly. Several genetic operators are
supplied and it is easy to add more. LibGA runs on many
systems/architectures. These include Unix, DOS, NeXT, and Amiga.
LibGA Version 1.00 is available by FTP from
ftp.aic.nrl.navy.mil/pub/galist/src/ga/libga100.tar.Z or by email
request to its author, Art Corcoran <email@example.com>
LICE is a parameter OPTIMIZATION program based on EVOLUTION
STRATEGIEs (ES). In contrast to classic ES, LICE has a local
SELECTION scheme to prevent premature stagnation. Details and results
were presented at the EP'94 conference in San Diego. LICE is written
in ANSI-C (more or less), and has been tested on Sparc-stations and
Linux-PCs. If you want plots and graphics, you need X11 and gnuplot.
If you want a nice user interface to create parameter files, you also
LICE-1.0 is available as source code by FTP from
Author: Joachim Sprave <firstname.lastname@example.org>
The MathWorks FTP site has some Matlab GA code in the directory
ftp.mathworks.com/pub/contrib/v4/optim/genetic It's a bunch of .m
files that implement a basic GA. Contact: Andrew Potvin,
<email@example.com> for information.
mGA is an implementation of a messy GA as described in TCGA report
No. 90004. Messy GAs overcome the linkage problem of simple GENETIC
ALGORITHMs by combining variable-length strings, GENE expression,
messy operators, and a nonhomogeneous phasing of evolutionary
processing. Results on a number of difficult deceptive test
functions have been encouraging with the messy GA always finding
global optima in a polynomial number of function evaluations.
See TCGA reports 89003, 90005, 90006, and 91004, and IlliGAL report
91008 for more information on messy GAs (See Q14). The C language
version is available by FTP from IlliGAL in the directory
Contact: Dave Goldberg <firstname.lastname@example.org>
PARAGenesis is the result of a project implementing Genesis on the
CM-200 in C*. It is an attempt to improve PERFORMANCE as much as
possible without changing the behavior of the GENETIC ALGORITHM.
Unlike the punctuated equilibria and local SELECTION models,
PARAGenesis doesn't modify the genetic algorithm to be more
parallelizable as these modifications can drastically alter the
behavior of the algorithm. Instead each member is placed on a
separate processor allowing initialization, evaluation and MUTATION
to be completely parallel. The costs of global control and
communication in selection and CROSSOVER are present but minimized as
much as possible. In general PARAGenesis on an 8k CM-200 seems to run
10-100 times faster than Genesis on a Sparc 2 and finds equivalent
PARAGenesis includes all the features of serial Genesis plus some
additions. The additions include the ability to collect timing
STATISTICS, probabilistic selection (as opposed to Baker's stochastic
universal sampling), uniform crossover and local or neighborhood
selection. Anyone familiar with the serial implementation of Genesis
and C* should have little problem using PARAGenesis.
PARAGenesis is available by FTP from
DISCLAIMER: PARAGenesis is fairly untested at this point and may
contain some bugs.
Michael van Lent, Advanced Technology Lab, University of Michigan,
1101 Beal Av., Ann Arbor, MI 48109, USA. Net:
PGA is a simple testbed for basic explorations in GENETIC ALGORITHMs.
Command line arguments control a range of parameters, there are a
number of built-in problems for the GA to solve. The current set
o maximize the number of bits set in a CHROMOSOME
o De Jong's functions DJ1, DJ2, DJ3, DJ5
o binary F6, used by Schaffer et al
o a crude 1-d knapsack problem; you specify a target and a set of
numbers in an external file, GA tries to find a subset that sums
as closely as possible to the target
o the `royal road' function(s); a chromosome is regarded as a set of
consecutive blocks of size K, and scores K for each block entirely
filled with 1s, etc; a range of parameters.
o max contiguous bits, you choose the ALLELE range.
o timetabling, with various smart MUTATION options; capable of
solving a good many real-world timetabling problems (has done so)
Lots of GA options: rank, roulette, tournament, marriage-tournament,
spatially-structured SELECTION; one-point, two-point, uniform or no
CROSSOVER; fixed or adaptive mutation; one child or two; etc.
Default output is curses-based, with optional output to file; can be
run non-interactively too for batched series of experiments.
It's easy to add your own problems. Chromosomes are represented as
character arrays, so you are not (quite) stuck with bit-string
PGA has been used for teaching for a couple of years now, and has
been used as a starting point by a fair number of people for their
own projects. So it's reasonably reliable. However, if you find bugs,
or have useful contributions to make, Tell Me! It is available by FTP
from ftp.dai.ed.ac.uk/pub/pga/pga-3.1.tar.gz (see the file pga.README
in the same directory for more information)
Peter Ross, Department of AI, University of Edinburgh, 80 South
Bridge, Edinburgh EH1 1HN, UK. Net: <email@example.com>
PGAPack is a general-purpose, data-structure-neutral parallel GENETIC
ALGORITHM library. It is intended to provide most capabilities
desired in a genetic algorithm library, in an integrated, seamless,
and portable manner.
o Callable from Fortran or C.
o Runs on uniprocessors, parallel computers, and workstation
o Binary-, integer-, and real- and character-valued native data
o Full extensibility to support custom operators and new data types.
o Easy-to-use interface for novice and application users.
o Multiple levels of access for expert users.
o Extensive debugging facilities.
o Large set of example problems.
o Detailed users guide
o Parameterized POPULATION replacement.
o Multiple choices for SELECTION, CROSSOVER, and MUTATION operators
o Easy integration of hill-climbing heuristics.
Availability: PGAPack is freely available and may be obtained by FTP
from info.mcs.anl.gov/pub/pgapack/pgapack.tar.Z or from
Further Information from David Levine, Mathematics and Computer
Science Division, Argonne National Laboratory, Argonne, Illinois
60439, (708)-252-6735 <firstname.lastname@example.org>
REGAL (RElational Genetic Algorithm Learner) is a distributed GA-
based system, designed for learning multi-modal First Order Logic
concept descriptions from examples. REGAL is based on a SELECTION
operator, called Universal Suffrage operator, provably allowing the
POPULATION to asymptotically converge, on average, to an equilibrium
state, in which several SPECIES coexist. REGAL makes use of PVM 3.3
and Tcl/Tk. This version of REGAL is provided with a graphical user
interface developed in Tcl/Tk language.
REGAL has been jointly developed by: Attilio Giordana
<email@example.com> http://www.di.unito.it/~attilio/ and Filippo
Neri <firstname.lastname@example.org> http://www.di.unito.it/~neri/ at the
University of Torino, Dipartimento di Informatica, Italy.
Neri F. and Giordana A. (1995). "A Distributed Genetic Algorithm
for Concept Learning", Proc. Int. Conf. on Genetic Algorithms
(Pittsburgh, PA), Morgan Kaufmann, pp. 436-443.
Neri F. and Saitta L. (1995). "A Formal Analysis of
Selection Schemes". Proc. Int. Conf. on Genetic Algorithms
(Pittsburgh,PA), Morgan Kaufmann, pp. 32-39 .
Giordana A. and Neri F. (1996). "Search-Intensive Concept
Induction". Evolutionary Computation
Journal, MIT Press, vol. 3, n. 4, pp. 375 - 416.
Neri F. and Saitta L. (1997). "An Analysis of the
Universal Suffrage Selection Operator". Evolutionary Computation
Journal, MIT Press, vol. 4, n. 1, pp. 89-109.
SGA-C is a C-language translation and extension of the original
Pascal SGA code presented in Goldberg's book [GOLD89]. It has some
additional features, but its operation is essentially the same as
that of the Pascal version. SGA-C is described in TCGA report No.
SGA-Cube is a C-language translation of Goldberg's SGA code with
modifications to allow execution on the nCUBE 2 Hypercube Parallel
Computer. When run on the nCUBE 2, SGA-Cube can take advantage of
the hypercube architecture, and is scalable to any hypercube
dimension. The hypercube implementation is modular, so that the
algorithm for exploiting parallel processors can be easily modified.
In addition to its parallel capabilities, SGA-Cube can be compiled on
various serial computers via compile-time options. In fact, when
compiled on a serial computer, SGA-Cube is essentially identical to
SGA-C. SGA-Cube is described in TCGA report No. 91005.
Each of these programs is distributed in the form of a Unix shar
file, available via e-mail or on various formatted media by request
from: Robert Elliott Smith, Department of Engineering of Mechanics,
Room 210 Hardaway Hall,, The University of Alabama P.O. Box 870278,
Tuscaloosa, Alabama 35487, USA. Net: <email@example.com>
SGA-C and SGA-Cube are also available in compressed tar form by FTP
from ftp.aic.nrl.navy.mil/pub/galist/src/ga/sga-c.tar.Z and sga-
Splicer is a GENETIC ALGORITHM tool created by the Software
Technology Branch (STB) of the Information Systems Directorate at
NASA/Johnson Space Center with support from the MITRE Corporation.
Splicer has well-defined interfaces between a GA kernel,
representation libraries, FITNESS modules, and user interface
The representation libraries contain functions for defining,
creating, and decoding genetic strings, as well as multiple CROSSOVER
and MUTATION operators. Libraries supporting binary strings and
permutations are provided, others can be created by the user.
Fitness modules are typically written by the user, although some
sample applications are provided. The modules may contain a fitness
function, initial values for various control parameters, and a
function which graphically displays the best solutions.
Splicer provides event-driven graphic user interface libraries for
the Macintosh and the X11 window system (using the HP widget set); a
menu-driven ASCII interface is also available though not fully
supported. The extensive documentation includes a reference manual
and a user's manual; an architecture manual and the advanced
programmer's manual are currently being written.
An electronic bulletin board (300/1200/2400 baud, 8N1) with
information regarding Splicer can be reached at (713) 280-3896 or
(713) 280-3892. Splicer is available free to NASA and its
contractors for use on government projects by calling the STB Help
Desk weekdays 9am-4pm CST at (713) 280-2233. Government contractors
should have their contract monitor call the STB Help Desk; others may
purchase Splicer for $221 (incl. documentation) from: COSMIC, 382 E.
Broad St., Athens, GA 30602, USA. (Unverified 8/94). Last known
address <firstname.lastname@example.org> (Steve Bayer). This now bounces
back with "user unknown".
TOLKIEN (TOoLKIt for gENetics-based applications) is a C++ class
library, intended for those involved in GAs and CLASSIFIER SYSTEM
research with a working knowledge of C++. It is designed to reduce
effort in developing genetics-based applications by providing a
collection of reusable objects. For portability, no compiler
specific or class library specific features are used. The current
version has been compiled successfully using Borland C++ Version 3.1
and GNU C++.
TOLKIEN contains a lot of useful extensions to the generic GENETIC
ALGORITHM and classifier system architecture. Examples include: (i)
CHROMOSOMEs of user-definable types; binary, character, integer and
floating point; (ii) Gray code encoding and decoding; (iii) multi-
point and uniform CROSSOVER; (iv) diploidy and dominance; (v) various
SELECTION schemes such as tournament selection and linear ranking;
(vi) linear FITNESS scaling and sigma truncation; (vii) the simplest
one-taxon-one-action classifiers and the general two-taxa-one-action
TOLKIEN is available from ENCORE (See Q15.3) in file:
GA/src/TOLKIEN.tar.gz The documentation and two primers on how to
build GA and CFS applications alone are available as:
Author: Anthony Yiu-Cheung Tang <email@example.com>, Department of
Computer Science (Rm 913), The Chinese University of Hong Kong. Tel:
This is a Windows 3.1 artificial neural netwrk and GA program
(shareware). TDL allows users to perform pattern recognition by
utilizing software that allows for fast, automatic construction of
Neural Networks, mostly alleviating the need for parameter tuning.
Evolutionary processes combined with semi-weighted networks (hybrid
cross between standard weighted neurons and weightless n-level
threshold units) generally yield very compact networks (i.e., reduced
connections and hidden units). By supporting multi-shot learning over
standard one-shot learning, multiple data sets (characterized by
varying input and output dimensions) can be learned incrementally,
resulting in a single coherent network. This can also lead to
significant improvements in predictive accuracy (Trans-dimensional
generalization). Graphical support and several data files are also
Available on the WWW from: http://pages.prodigy.com/upso
For further details contact: <firstname.lastname@example.org>
This is a simulator for the G/SPLINES (genetic spline models)
algorithm which builds spline-based functional models of experimental
data, using CROSSOVER and MUTATION to evolve a POPULATION towards a
better fit. It is derived from Friedman's MARS models. The original
work was presented at ICGA-4, and further results including
additional basis function types such as B-splines have been presented
at the NIPS-91 meeting.
This program used to be available free by FTP from
riacs.edu/pub/wolf-4.0.tar.Z (However this machine no longer allows
anonymous ftp access, so you wont be able to get it from there any
more. If anyone knows anywhere this code is freely available from,
let us know. Ed.) Runs on SUN (and possibly any SYSV) UNIX box. Can
be redistributed for noncommercial use. Simulator includes executable
and C source code; a technical report (RIACS tech report 91.10) is
David Rogers, MS Ellis, NASA Ames Research Center, Moffett Field, CA
94035, USA. Net: <email@example.com> (Note - this address may be
XGenetic is an ActiveX control for the implementation of a GENETIC
ALGORITHM in any language that accepts ActiveX interfaces. Such
languages include, but are not limited to: Visual Basic, Visual C++,
Delphi, etc. Written in Visual Basic 6.0, XGenetic is flexible in
implementation to allow the user to easily define the parameters for
their particular scenario, be it forecasting, scheduling, or the
myriad of other uses for the genetic algorithm.
Features: ( ** indicates registered version only)
o Data Types: Bit, Integer, Real
o Selection Operators: Roulette, Tournament **, Stochastic Universal
Sampling **, Truncation **, Random **
o Crossover Operators: N-Point (1 point, 2 point, 3 point, etc),
Uniform **, Arithmetic **
o Mutation Operators: Uniform, Boundary **
There are two versions of the software available. The shareware
version of the product is available freely off the net(address
below). It includes the program file(xgen.ocx) and
documentation(including a sample program) in three formats. The
registered version is available from the author directly for a
registration fee of $50. Commercial licences may be negotiated with
the author. The shareware version may be downloaded from:
For further information, contact the author, Jeff Goslin, by email:
<firstname.lastname@example.org>, or by snail-mail: 27842 Flanders Ave, Warren
MI 48093, USA.
CFS-C 1.0 is a domain independent collection of CLASSIFIER SYSTEM
routines written by Rick L. Riolo <email@example.com> as part of his PhD
dissertation. A completely rewritten CFS-C is planned for 1994/95;
this may include the features of CFS-C 2.0 mentioned in [SAB90] (e.g.
"latent learning") or they may be included in a separate package
released in 1995. An ANSIfied version of CFS-C 1.0 (CFS-C 1.98j) is
available by FTP.
CFS-C is available from ENCORE (See Q15.3) in file:
CFS/src/cfsc-1.98j.tar.gz and includes the original 1.02 CFS-C in its
"cfsc/orig" folder after unpacking. On the "SyS" FTP server its:
documentation in /pub/LCS/docs/cfsc.ps.gz
Another version of CFS-C (version XV 0.1) by Jens Engel
<firstname.lastname@example.org> is also available. This includes
bug fixes of earlier versions, allowing it to run on a wider range of
machines (e.g. Linux and nCUBE). It also has an XView front end that
makes it easier to control, and some extensions to the algorithms.
It is available from Encore in file: CFS/src/cfscxv-0.1.tar.gz with
documentation in CFS/docs/cfscxv-0.1.readme.gz
Rick L. Riolo (1988) "CFS-C: A package of domain independent
subroutines for implementing classifier systems in arbitrary, user-
defined environments", Logic of computers group, Division of computer
science and engineering, University of Michigan.
Rick L. Riolo (1988) "LETSEQ: An implementation of the CFS-C
classifier-system in a task-domain that involves learning to predict
letter sequences", Logic of computers group, Division of computer
science and engineering, University of Michigan.
Rick L. Riolo (1988) "CFS-C/FSW1: An implementation of the CFS-C
classifier system in a task domain that involves learning to traverse
a finite state world", Logic of computers group, Division of computer
science and engineering, University of Michigan.
SCS-C is a (`mostly ANSI') C language translation and extension of
Goldberg's Simple CLASSIFIER SYSTEM, as presented in Appendix D in
his seminal book [GOLD89].
SCS-C has been developed in parallel on a Sun 10/40 and an ATARI ST,
and thus should be quite portable; it's distributed free of charge
under the terms of the GNU General Public License. Included are some
additional goodies, e.g. the VAX/VMS version of SCS, rewritten in C
by Erik Mayer <email@example.com>.
SCS-C v1.0j is available from ENCORE (See Q15.3), by FTP in file
For more information contact: Joerg Heitkoetter, UUnet Deutschland
GmbH, Techo-Park, Emil-Figge-Str. 80, D-44227 Dortmund, Germany.
Subject: Q20.2: Commercial software packages?
ActiveGA is an activeX (OLE) control that uses a GENETIC ALGORITHM to
find a solution for a given problem. For example, you can insert an
ActiveGA control into Microsoft Excel 97 and have it optimize your
o OPTIMIZATION Mode: Minimize, Maximize or Closest To
o SELECTION Mode: Tournament, Roulette Wheel
o User defined POPULATION size, MUTATION rate and other parameters
o Event driven, cancelable iteration
o Invisible at run time
o Excel 97, Visual Basic, Visual C++ samples
Various samples are available for free download. For these and
further information, see
http://www.brightsoft.com/products/activega.htm or contact
Brightwater Software <firstname.lastname@example.org>. For a limited time
the ActiveGA costs $99 per developer. ActiveGA has no run time
Logica Cambridge Ltd. developed EnGENEer as an in-house GENETIC
ALGORITHM environment to assist the development of GA applications on
a wide range of domains. The software was written in C and runs under
Unix as part of a consultancy and systems package. It supports both
interactive (X-Windows) and batch (command-line) modes of operation.
EnGENEer provides a number of flexible mechanisms which allow the
developer to rapidly bring the power of GAs to bear on new problem
domains. Starting with the Genetic Description Language, the
developer can describe, at high level, the structure of the ``genetic
material'' used. The language supports discrete GENEs with user
defined cardinality and includes features such as multiple
CHROMOSOMEs models, multiple SPECIES models and non-evolvable parsing
symbols which can be used for decoding complex genetic material.
The user also has available a descriptive high level language, the
Evolutionary Model Language. It allows the description of the GA type
used in terms of configurable options including: POPULATION size,
population structure and source, SELECTION method, CROSSOVER and
MUTATION type and probability, INVERSION, dispersal method, and
number of OFFSPRING per GENERATION.
Both the Genetic Description Language and the Evolutionary Model
Language are fully supported within the interactive interface
(including online help system) and can be defined either "on the fly"
or loaded from audit files which are automatically created during a
Monitoring of GA progress is provided via both graphical tools and
automatic storage of results (at user defined intervals). This allows
the user to restart EnGENEer from any point in a run, by loading both
the population at that time and the evolutionary model that was being
Connecting EnGENEer to different problem domains is achieved by
specifying the name of the program used to evaluate the problem
specific FITNESS function and constructing a simple parsing routine
to interpret the genetic material. A library of standard
interpretation routines are also provided for commonly used
representation schemes such as gray-coding, permutations, etc. The
fitness evaluation can then be run as either a slave process to the
GA or via a standard handshaking routines. Better still, it can be
run on either the machine hosting the EnGENEer or on any sequential
or parallel hardware capable of connecting to a Unix machine.
For more information, contact: George Robbins, Systems Intelligence
Division, Logica Cambridge Ltd., Betjeman House, 104 Hills Road,
Cambridge CB2 1LQ, UK. Tel: +44 1716 379111, Fax: +44 1223 322315
EvoFrame is to EVOLUTION STRATEGIEs what MicroGA is to GENETIC
ALGORITHMs, a toolkit for application development incorporating ESs
as the OPTIMIZATION engine.
EvoFrame is an object oriented implemented programming tool for
evolution strategies (Rechenberg/Schwefel, Germany) for easy
implementation and solution of numerical and combinatorical problems.
EvoFrame gives you freedom of implementing every byte of the
optimization principle and its user interface. You can focus on the
optimization problem and forget about all the rest.
EvoFrame is available as Version 2.0 in Borland-Pascal 7.0 and Turbo-
Vision for PC's and as Version 1.0 in C++ for Apple Macintosh using
MPW and MacApp. Both implementations allow full typed
implementation, i.e. no more translation from problem specific
format to an optimization specific one. A prototyping tool (cf
REALizer) exists for both platforms too.
EvoFrame allows pseudoparallel optimization of many problems at once
and you can switch optimization parameters and internal methods (i.e.
quality function etc.) during runtime and during optimization cycle.
Both tools can be modified or extended by overloading existing
methods for experimental use. They are developed continously in
correlation to new research results.
The PC version is prepared for experimental use due to a
comprehensive protocolling mechanism of optimzation cycles and user
data. It also allows compilation of executable files with different
complexity by setting conditional compilation flags. It can be used
with 3 levels of stacked POPULATIONs.
The Mac version is the more complex (recursive) implementation. It
allows stacking of any number of populations for modelling of complex
systems. Theory stops at multipopulation level at the time. EvoFrame
for Mac is ready for the future, allowing any number of population
Ask for porting the Mac version (C++) to any other platform, i.e. X
REALizer is a tool for rapid prototyping of EvoFrame applications.
It's an override of the corresponding framework which is prepared to
optimize using a vector of real numbers. All methods for standard
EVOLUTION and file handling, etc. are ready implemented. The
remaining work for the user is to define a constant for the problem
size, fill in the quality function and start the optimization
For further information, current prices and orders, contact: Wolfram
Stebel, Optimum Software, Braunfelser Str. 26, 35578 Wetzlar,
Germany. Net: <email@example.com>
Evolver is a GENETIC ALGORITHM package for Windows. Beginners can use
the Excel add-in to model and solve problems from within Excel.
Advanced users can use the included Evolver API to build custom
applications that access any of the six different genetic algorithms.
Evolver can be customized and users can monitor progress in real-time
graphs, or change parameters through the included EvolverWatcher
program. The package costs $349 (or UKP350), comes on two 3.5"
disks, and includes support for Visual Basic. For further information
or to order, contact: Palisade Corp, (607) 277-8000
http://www.palisade.com or Palisade Europe <sales@palisade-
europe.com>, Tel +44 1752 204310 http://www.palisade-europe.com
FlexTool(GA) is a modular software tool which provides an ENVIRONMENT
for applying GA to diverse domains with minimum user interaction and
Version M2.2 is the MATLAB version which provides a total GA based
design and development environment in MATLAB. MATLAB provides us with
an interactive computation intensive environment. The high level,
user friendly programming language combined with built-in functions
to handle matrix algebra, Fourier series, and complex valued
functions provides the power for large scale number crunching.
The GA objects are provided as .m files. FlexTool(GA) Version M2.2 is
designed with emphasis on modularity, flexibility, user friendliness,
environment transparency, upgradability, and reliability. The design
is engineered to evolve complex, robust models by drawing on the
power of MATLAB.
FlexTool(GA) Version M2.2 Features:
BUILDING BLOCK : Upgrade to EFM or ENM or CI within one year
Niching module : to identify multiple solutions
Clustering module : Use separately or with Niching module
Optimization : Single and Multiple Objectives
Flex-GA : Very fast proprietary learning algorithm
GA : Modular, User Friendly, and System Transparent
GUI : Easy to use, user friendly
Help : Online
Tutorial : Hands-on tutorial, application guidelines
Parameter Settings : Default parameter settings for the novice
General : Statistics, figures, and data collection
Compatibility : FlexTool product suite
GA options : generational, steady state, micro, Flex-GA
Coding schemes : include binary, logarithmic, real
Selection : tournament, roulette wheel, ranking
Crossover : include 1, 2, multiple point crossover
Compatible to : FlexTool(GA) M1.1 Genetic Algorithms Toolbox
The FlexTool product suite includes various soft computing BUILDING
CI: Computational Intelligence http://www.flextool.com/ftci.html
EFM: Evolutionary Fuzzy Modeling http://www.flextool.com/ftefm.html
ENM: Evolutionary Neuro Modeling http://www.flextool.com/ftenm.html
FS : Fuzzy Systems http://www.flextool.com/ftfs.html
EA : EVOLUTIONARY ALGORITHMs http://www.flextool.com/ftga.html
NN : Neural Networks http://www.flextool.com/ftnn.html
For information contact <firstname.lastname@example.org> http://www.flextool.com
GAME (GA Manipulation Environment) aims to demonstrate GA
applications and build a suitable programming ENVIRONMENT.
GAME is being developed as part of the PAPAGENA project of the
European Community's Esprit III initiative.
GAME is available as an addendum to a book on PGAs (cf PAPAGENA,
Q20.3). And from the project's FTP server
bells.cs.ucl.ac.uk/papagena/ e.g. "papagena/game/docs" contains all
the papers that have been produced over the course of the GAME
project. The sources can also be obtained by FTP see
GAME is now in version 2.01. This version is still able to run only
sequential GAs, but version 3.0 will handle parallel GAs as well.
Unfortunately, The project yet only produced a Borland C++ 3.x
version, so far. It is intended to distribute a version for UNIX/GNU
C++ as well, when some compatibility issues concerning C++
"standards" have been resolved. Afterward a UNIX version will be
released, but this will be only happen after the release of PC
For more information contact: Jose Luiz Ribeiro Filho, Department of
Computer Science, University College London, Gower Street, London
WC1E 6BT, UK. Net: <email@example.com> (Unverified 8/94).
GeneHunter from Ward Systems runs on a PC under Windows. It is
callable from Microsoft Excel 5 spreadsheets, and accessible via
function calls in a dynamic link library. The DLL is designed
especially for Visual Basic, but runs with other languages which call
DLLs under Windows 3.1 such as Visual C++. 16- and 32-bit versions
are available. GeneHunter can also integrate with Ward's neural
network software. Cost $369.
For full details, see http://www.wardsystems.com/ or contact: Ward
Systems Group Inc, Executive Park West, 5 Hillcrest Drive, Frederick,
MD 21703, USA. 301-662-7950 <firstname.lastname@example.org>
GENERATOR is a GENETIC ALGORITHM package designed to interact with
Microsoft Excel for Windows. Users are able to define and solve
problems using Excel formulas, tables and functions. FITNESS is
easily defined as an Excel formula or optionally a macro. Progress
can be monitored using GENERATOR's real-time fitness graph and status
window as well as user-defined Excel graphs. GENERATOR can be paused
at any time to allow adjustment of any of the parameters and then
o Multiple GENE types: integer, real and permutation.
o Combined roulette-wheel and elitist SELECTION method.
o ELITISM is optional and adjustable.
o None, two-point, and a proprietary permutation CROSSOVER.
o Random, Random Hillclimb and Directional Hillclimb MUTATION
o Special hillclimbing features to find solutions faster.
o fitness goal: maximize, minimize or seek value.
o Convergence: duplicates not allowed.
o Real-Time alteration of parameters relating to crossover,
mutation, POPULATION, etc.
o Real-Time progress graph of Best, Worst and Median fitness.
o fitness defined using an Excel formula or macro.
The parameters available to the user include mutation probability for
population and genes, control of mutation limit per gene, control of
hillclimbing, population size, elite group size, RECOMBINATION
method, and mutation technique.
Connecting generator to problems defined on the Excel spreadsheet is
achieved by first specifying the spreadsheet locations of the gene
group cells and their type, and lastly, the location of the formula
used to evaluate the problem-specific fitness function.
GENERATOR requires at least a 386 IBM compatible PC with 2 MB of RAM,
Windows 3.0 (or later) and Microsoft Excel 4.0 (or later). A
comprehensive manual includes an explanation of genetic algorithms
and several tutorial example problems. The $379 package.includes
GENERATOR on a 3.5" diskette, the manual, and free customer support.
For further information or to order, contact: New Light Industries,
Ltd.; 9713 W. Sunset Hwy; Spokane, WA USA 99204 Tel: (509) 456-8321;
Fax (509) 456-8351; E-mail: <email@example.com> WWW page:
Genetic Server and Genetic Library:
Genetic Server and Genetic Library are tools that allow programmers
to embed GENETIC ALGORITHMs into their own applications. Both
products provide a flexible yet intuitive API for genetic algorithm
design. Genetic Server is an ActiveX component designed to be used
within a Visual Basic (or VBA) application and Genetic Library is a
C++ library designed to be used within a Visual C++ application.
There are no royalties for distributing applications built using
Genetic Server or Genetic Library.
o Data types: Binary, Integer, and Real
o Progression types: Generational, Steady State
o SELECTION operators: Roulette (FITNESS or Rank), Tournament, Top
Percent, Best, and Random
o CROSSOVER operators: One Point, Two Point, Uniform, Arithmetic,
o MUTATION operators: Flip Bit, Boundary, Non-Uniform, Uniform, and
o Termination Methods: GENERATION Number, EVOLUTION Time, Fitness
Threshold, Fitness Convergence, POPULATION Convergence, and GENE
o User-defined selection, crossover, and mutation operators (Genetic
For more information or to place an order, contact: NeuroDimension,
Inc., 1800 N. Main Street, Suite #D4, Gainesville, FL 32609. Voice:
(800) 634-3327, Fax: (352) 377-9009. Email: <firstname.lastname@example.org> Web site:
MicroGA is a powerful and flexible new tool which allows programmers
to integrate GAs into their software quickly and easily. It is an
object-oriented C++ framework that comes with full source code and
documentation as well as three sample applications. Also included is
the Galapagos code generator which allows users to create complete
applications interactively without writing any C++ code, and a sample
MicroGA is available for Macintosh II or higher with MPW and a C++
compiler, and also in a Microsoft Windows version for PC compatibles.
Compiled applications made with MicroGA can be sold without license
fee. MicroGA is priced at $249.
Galapagos is a tool for use with Emergent Behavior's MicroGA Toolkit.
It allows a user to define a function and set of constraints for a
problem that the user wants to solve using the GA. Galapagos then
generates a complete C++ program using the information supplied. Then
all the user has to do is to compile these files, using either
Turbo/Borland C++ (PC, MS Windows), or MPW and C++ compiler
(Macintosh), and link the resulting code to the MicroGA library. Then
just run the program. Galapagos comes free with every copy of
For further information and orders, contact: Steve Wilson, Emergent
Behavior, 635 Wellsbury Way, Palo Alto, CA 94306, USA. Net:
MicroGA is distributed in Germany by Optimum Software (cf EvoFrame &
The Omega Predictive Modeling System, marketed by KiQ Limited, is a
powerful approach to developing predictive models. It exploits
advanced GA techniques to create a tool which is "flexible, powerful,
informative and straightforward to use". Omega is geared to the
financial domain, with applications in Direct Marketing, Insurance,
Investigations and Credit Management. The ENVIRONMENT offers
facilities for automatic handling of data; business, statistical or
custom measures of PERFORMANCE, simple and complex profit modeling,
validation sample tests, advanced confidence tests, real time
graphics, and optional control over the internal GA.
For further information, contact: KiQ, Business Modeling Systems
Ltd., Easton Hall, Great Easton, Essex CM6 2HD, UK. Tel: +44 1371
870254 (Unverified 8/94).
OOGA (Object-Oriented GA) is a GENETIC ALGORITHM designed for
industrial use. It includes examples accompanying the tutorial in
the companion "Handbook of Genetic Algorithms". OOGA is designed such
that each of the techniques employed by a GA is an object that may be
modified, displayed or replaced in object-oriented fashion. OOGA is
especially well-suited for individuals wishing to modify the basic GA
techniques or tailor them to new domains.
The buyer of OOGA also receives Genesis (see above). This release
sports an improved user interface. OOGA and Genesis are available
together on 3.5'' or 5.25'' disk for $60 ($52.50 inside North
America) by order from: The Software Partnership (T.S.P.), P.O. Box
991, Melrose, MA 02176, USA. Tel: +1 617 662 8991 (Unverified 8/94).
optiGA for VB is an ActiveX control (OCX) for the implementation of
GENETIC ALGORITHMs. It is described by the author, Elad Salomons, as
No matter what the nature of your OPTIMIZATION problem might be,
optiGA is a generic control that will perform the genetic run for
you. With very little coding needed, you can be up and running in no
time. Just define your variables (binary, real or integers), code
the FITNESS function and you are set to go. On the other hand, you
can override optiGA's default parameters and select from several of
REPRODUCTION OPERATORs such as: SELECTION methods, CROSSOVER methods,
MUTATION methods and many controlling parameters.
If that isn't enough, optiGA can grow with you: Did you come up with
a new crossover method and wanted to try it? Have you read the
latest article about an interesting mutation method that you want to
implement? No problem! Just use the "User Defined" crossover and
mutation events and code them yourself.
optiGA was written in "Visual Basic" and can be used with VB and all
Visit optiGA's site for more information end an evaluation version
PC-Beagle is a rule-finder program for PCs which examines a database
of examples and uses machine-learning techniques to create a set of
decision rules for classifying those examples, thus turning data into
knowledge. The system contains six major components, one of which
(HERB - the "Heuristic Evolutionary Rule Breeder") uses GA techniques
to generate rules by natural SELECTION.
PC-Beagle is available to educational users for 69 pounds sterling.
Orders, payment or requests for information should be addressed to:
Richard Forsyth, Pathway Research Ltd., 59 Cranbrook Rd., Bristol BS6
7BS, UK. Tel: +44 117 942 8692 (Unverified 8/94).
XpertRule GenAsys is an expert system shell with embedded GENETIC
ALGORITHM marketed by Attar Software. Targeted to solve scheduling
and design applications, this system combines the power of genetic
algorithms in evolving solutions with the power of rule-based
programming in analyzing the effectiveness of solutions. Rule-based
programming can also be used to generate the initial POPULATION for
the genetic algorithm and for post-optimization planning. Some
examples of design and scheduling problems which can be solved by
this system include: OPTIMIZATION of design parameters in electronic
and avionic industries, route optimization in the distribution
sector, production scheduling in manufacturing, etc.
For further information, contact: Attar Software, Newlands Road,
Leigh, Lancashire, UK. Tel: +44 1942 608844.
<100116.1547@CompuServe.com> http://www.attar.com (confirmed 3/96).
XYpe (The GA Engine) is a commercial GA application and development
package for the Apple Macintosh. Its standard user interface allows
you to design CHROMOSOMEs, set attributes of the genetic engine and
graphically display its progress. The development package provides a
set of Think C libraries and include files for the design of new GA
applications. XYpe supports adaptive operator weights and mixtures of
alpha, binary, gray, ordering and real number codings.
The price of $725 (in Massachusetts add 5% sales tax) plus $15
shipping and handling includes technical support and three
documentation manuals. XYpe requires a Macintosh SE or newer with
2MB RAM running OS V6.0.4 or greater, and Think C if using the
Currently the GA engine is working; the user interface will be
completed on demand. Interested parties should contact: Ed Swartz,
Virtual Image, Inc., 75 Sandy Pond Road #11, Ayer, MA 01432, USA.
Tel: +1 (508) 772-4225 (Unverified 8/94).
Subject: Q20.3: Current research projects?
The European ESPRIT III project PAPAGENA is pleased to announce the
availability of the following book and software:
Parallel Genetic Algorithms: Theory and Applications was recently
published by IOS press. The book, edited by Joachim Stender, provides
an overview of the theoretical, as well as practical, aspects
involved in the study and implementation of parallel GENETIC
The book comes with a floppy disk version of GAME (Genetic Algorithm
Manipulation Environment). For more information see the section on
GAME in Q20.2.
PeGAsuS is a general programming environment for evolutionary
algorithms. developed at the German National Research Center for
Computer Science. Written in ANSI-C, it runs on MIMD parallel
machines, such as transputers, and distributed systems, as well as
The Library contains GENETIC OPERATORs, a collection of FITNESS
functions, and input/output and control procedures. It provides the
user with a number of validated modules. Currently, PeGAsuS can be
compiled with the GNU C, RS/6000 C, ACE-C, and Alliant's FX/2800 C
compilers. It runs on SUNs and RS/6000 workstations, as well as on
the Alliant FX/28. PeGAsuS is not available to the public.
For more information contact: Dirk Schlierkamp-Voosen, Research Group
for Adative Systems, German National Research Center for Computer
Science, 53731 Sankt Augustin, Germany. Net: <dirk.schlierkamp-
Copyright (c) 1993-2000 by J. Heitkoetter and D. Beasley, all rights
This FAQ may be posted to any USENET newsgroup, on-line service, or
BBS as long as it is posted in its entirety and includes this
copyright statement. This FAQ may not be distributed for financial
gain. This FAQ may not be included in commercial collections or
compilations without express permission from the author.
End of ai-faq/genetic/part5