Abstract

Many seemingly different problems in artificial intelligence, symbolic processing, and machine learning can be viewed as requiring discovery of a computer program that produces some desired output for particular inputs. When viewed in this way, the process of solving these problems becomes equivalent to searching a space of possible computer programs for a most fit individual computer program. The new genetic programming paradigm described herein provides a way to search for this most fit individual computer program. In this new genetic programming paradigm, populations of computer programs are genetically bred using the Darwinian principle of survival of the fittest and using a genetic crossover (recombination) operator appropriate for genetically mating computer programs. In this paper, the process of formulating and solving problems using this new paradigm is illustrated using examples from various areas.

Citations

2888	Induction of Decision Trees - Quinlan - 1986
2304	Learning Internal Representations by Error Propagation - Rumelhart, Hinton, et al. - 1986
671	Adaptation in Natural and Artificial Systems. Ann Arbor - Holland - 1975
545	Some Studies in Machine Learning using the Game of Checkers - Samuel - 2000
402	Co-Evolving Parasites Improve Simulated Evolution as an Optimization Procddure”, physics D 42 - Hillis - 1990
290	Connectionist Learning Procedures - Hinton - 1990
181	Classifier systems and genetic algorithms - Booker, Goldberg, et al. - 1989
83	Learning with genetic algorithms: An overview - Jong - 1988
81	Flexible learning of problem solving heuristics through adaptive search - Smith - 1983
76	Ecological Diversity and Its Measurement - Magurran - 1988
71	AM: An Artificial Intelligence approach to discovery in mathematics - Lenat - 1976
54	Computer-Aided Gas Pipeline Operation using Genetic Algorithm and Rule Learning - Goldberg - 1989
50	Pattern recognizing control systems - Widrow, Smith - 1964
31	Data-driven approaches to empirical discovery - Langley, Zytkow - 1989
28	Action Networks - Nilsson - 1989
26	An empirical comparison of genetic and decisiontree classifiers - Quinlan - 1988
20	Genetic breeding of non-linear optimal control strategies for broom balancing - Koza, Keane - 1990
18	centering and broom balancing by genetically breeding populations of control strategy programs - Koza, Keane
18	Universal Subgoaling and Chunking - Laird, Rosenbloom, et al. - 1986
17	The original adaptive neural net broom-balancer - Widrow - 1987
14	The coevolution of automata - Miller - 1996
9	Cooperativity in networks of pattern recognizing stochastic learning automata.In Narendra,K.S. Adaptive and Learning Systems - Barto, Anandan, et al. - 1985
8	Bid competition and specificity reconsidered - Wilson - 1988
7	ECHO: Explorations of Evolution in a Minature World - Holland - 1990
6	CITIBASE: Citibank Economic Database (Machine Readable Magnetic Data File - Citibank - 1946
5	Non-linear genetic algorithms for solving problems by finding a fit composition of functions. Google Patents - KOZA - 1992
5	private communication - Nilsson
5	Classifier Systems and the animat problem - unknown authors - 1987
4	User's manual: RATS (Regression analysis of time series). Version 3.00 - Doan - 1988
4	The Genesys System: Evolution as a theme in artificial life - al - 1990
4	A genetic approach to econometric modeling." Sixth World Congress of the Econometric Society - Koza - 1990
4	Private communication - Rice - 1985
4	Hierarchical credit allocation in a classifier system - unknown authors - 1987
3	Special issue on genetic algorithms - Goldberg, Holland - 1988
2	Neural Networks for Artificial Intelligence - Hinton - 1988
2	Precursors of the P-star model. Economic Review - Humphrey - 1989
1	Genetic algorithms: A l0 year perspective. Proceedings of an International Conference on Genetic Algorithms and Their Applications - Norton
1	A learning machine: Part I. IBM Journal of Research and Development - Friedberg - 1966
1	Report on Program-Understanding Systems. Stanford Artificial Intelligence Laboratory memo AIM-240 - Progress - 1974
1	Application of the Genetic Algorithm to Automatic Program Generation. Master of Science Thesis - Study - 1989
1	Adaptive Computing System Capable of Learning and - Holland, Burks - 1987
1	Method of controlling a Classifier System. U.S. Patent 4,881,178. Issued November 14 - Holland, Burks - 1989
1	Econometric modeling by genetic breeding of mathematical functions - Koza - 1990
1	The evolution of automata in the repeated prisonerÕs dilemma - Miller - 1988
1	Using a small algebraic manipulation system to solve differential and integral equations by variational and approximation techniques - Mills - 1987
1	A Learning System Based on Genetic Adaptive Algorithms - Mateo - 1989
1	Tanese, Reiko. Distributed Genetic Algorithm for Function Optimization - Press - 1984