What is a Genetic Algorithm?

Optimization Based Upon Survival of the Fittest

A genetic algorithm is a search/optimization technique based on natural selection. Successive generations evolve more fit individuals, as according to the Darwinian theory of survival of the fittest. The genetic algorithm is a computer simulation of such evolution where the user provides the environment (function) in which the population must evolve.

Any users new to the GA world are encouraged to read David Goldberg's Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989.

Optimization Based Upon Survival of the Fittest
My Genetic Algorithm Story
As Told by Dr. David Carroll

My Genetic Algorithm Story

My first exposure to genetic algorithms was through Steven Levy's book entitled "Artificial Life." While making a frozen pizza one night, I realized that I could use this fascinating technique as a search method for some of my research. Imagine me with pizza cutter in raised hand saying, "Wow, I can automate my tedious two-week long trial and error search and simulate life at the same time!" (Pun intended, think about it.)

For some odd reason, it took me another month to figure out that the guy I played tennis with at the University of Illinois and the chap from the University of Alabama who wrote a marvelous GA textbook, were one and the same, David E. Goldberg (one of the "GA wizards").

With some tips from Goldberg, I concocted a fairly versatile and modern GA (maybe not so modern anymore, but still versatile and usable). The reason for this particular web page is twofold. First, I wrote a FORTRAN GA, whereas all of the other available free GAs I could find at the time were written in PASCAL, LISP or some version of C. Second, most (if not all) of the other readily available GAs do not include more modern GA concepts such as creep mutations, uniform crossover, niching, and elitism (whereas my GA has those options included). More recently I added the ability to use a micro-GA (very efficient). After many requests by colleagues and unknowns for my FORTRAN GA front-end driver code, I have decided to add this web page for any other FORTRAN holdouts (like myself) who are interested in GAs.

While my best version of the GA called the “securGA” used to be for sale (v.1.7.1), I am now offering it for free download. “secur” stands for small-elitist-creeping-uniform-restarting GA and all of my trials with the securGA always proved superior to other versions of my GA.

G. Yang, L. E. Reinstein, S. Pai, Z. Xu, D. L. Carroll, “A new genetic algorithm technique in optimization of permanent 125-I prostate implants”, Medical Physics, Vol. 25, No. 12, pp. 2308-2315, DOI n/a, (1998)
D. L. Carroll, “Chemical Laser Modeling with Genetic Algorithms”, AIAA Journal, Vol. 34, No. 2, pp. 338-346, DOI n/a, (1996)
D. L. Carroll, “Genetic Algorithms and Optimizing Chemical Oxygen-Iodine Lasers”, Developments in Theoretical and Applied Mechanics, Vol. 18, No., pp. 411-424, DOI n/a, (1996)

Additional Resources

Explore more on Genetic Algorithm. We have a free download of a driver and provide some useful tips and tricks.

Free Download

Download a free version of the GA Driver below.

Genetic Algorithm Tips

Tips and tricks for users to know.