Programming Computers by Means of Natural Selection
Professor
John R. Koza, Consulting Professor,
Computer Science Department, Stanford University, California
Genetic programming is an automatic technique for creating a computer program to solve a problem. Genetic programming applies the Darwinian principle of survival of the fittest to breed a population of computer programs. Starting with a primordial ooze of thousands of randomly created programs, a population of programs is progressively evolved over a series of generations by applying the principles of selective breeding and animal husbandry.
Genetic programming has been used to solve problems of robotics, optimisation, pattern recognition, classification, control, system identification, and design. There are a number of instances where genetic programming has produced a computer program that is competitive with human performance for a specific problem. These include problems from the fields of molecular biology, mathematics, and analogue electrical circuit design.
John R. Koza is consulting professor in the Computer Science Department and Symbolic Systems Program at Stanford University. At Stanford, he teaches courses on Genetic Algorithms and Genetic Programming, Artificial Life, and Computational Issues in Molecular Biology. He is author of the 1992 book Genetic Programming: On the Programming of Computers by Means of Natural Selection from the MIT Press, a 1994 book Genetic Programming II: Automatic Discovery of Reusable Programs from the MIT Press, over 100 articles, and is currently working on a third book on genetic programming. He received his PhD. in Computer Science from the University of Michigan under John Holland in 1972.