What is a Genetic Algorithm?
” So, what is it? What good is it? How does it work? Where did it come from? How has the GA evolved? Clearly the word “genetic” implies something biological and the word “algorithm” implies something mathematical or computational. Together, the words “genetic algorithm” essentially indicate a biological simulation. So, on a very basic level, a genetic algorithm, GA for short, is a simulation of Darwinian “survival of the fittest,” that is, a simulation of genetic evolution. What good is it? OK, that is what a GA is, now what good is it? Well it can clearly be useful for biologists who want to try and simulate some sort of genetic evolution process on a computer. However, this is a somewhat restricted application of a GA. From an engineering stand point (and I’m an engineer), the GA can be used as a robust search and optimization procedure based on genetic evolutionary principles to search for a global maximum (or minimum, depending on your problem). Over the past few years I’ve been ta
Everybody wants to get a handle on how to make things happen with a computer. Maybe you just want a program to help you understand something (like how your money gets spent every month); maybe you want your computer to control something (like a robot on Mars). Sometimes it takes a very simple procedure to make a computer represent something. If you’re lucky, you simply find an equation and implement it in some programming language that you’ve got a handle on. Unfortunately, the problems that programmers and other analytical types want to find solutions for outstrip our fundamental prediction abilities. There is this inverse problem: How can I move from just a pile of data to an equation that describes it?. It’s dang hard. Oh sometimes it’s easy to plug in data. X+3 = 7. (Uh, 4?). But try to find the values for this guy: X^2 + 3*X + Y^3 – 16 + 5Z + 2X + 13Y = 42 “Yo, Pat, Mr. Topnhat needs an answer to this by tomorrow. I told him you’d get right on it.” “Okay, let me call my High Schoo
A genetic algorithm is any type of software that uses variation and selection to produce an evolutionarily tuned output. That output may be a program, a value, or even a picture. The genetic algorithm needs a process for generating new variants and feedback, or fitness criteria, in order to determine which variants to discard and which to use. For example, imagine a genetic algorithm designed to create images of fictional insects. The initial output is merely a hodgepodge of randomly connected lines. Based on feedback from human operators, images that look nothing like insects are eliminated, and future variations tend to look more and more insect-like. As the outputs become more finely tuned, they eventually begin to look something like insects. The genetic algorithm is often mentioned in connection with Alife, or artificial life, which is the study of virtual organisms created in a computer. These virtual organisms usually live on a virtual grid, and sometimes even reproduce with eac
Briefly, a genetic algorithm is a process which starts with an initial population of individual sets of ‘random’ characteristics. The sets are partitioned, and the first part of a set is combined with the second part of another to generate a new hybrid set that has a combination of characteristics from the parents. Selection: If any set is determined (by some method) to be more successful, it is copied and used to generate more new sets. The less successful sets are not propagated (as much) or destroyed. As the process is repeated, the generations become more successful–the population evolves towards the successful characteristics.
Very briefly, a genetic algorithm is a search/optimization technique based on natural selection. Successive generations evolve more fit individuals based on Darwinian 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.
