Genetic Programming: On the Programming of Computers by Means of Natural Selection

Front Cover
MIT Press, 1992 - Computers - 819 pages

In this ground-breaking book, John Koza shows how this remarkable paradigm works and provides substantial empirical evidence that solutions to a great variety of problems from many different fields can be found by genetically breeding populations of computer programs.

Genetic programming may be more powerful than neural networks and other machine learning techniques, able to solve problems in a wider range of disciplines. In this ground-breaking book, John Koza shows how this remarkable paradigm works and provides substantial empirical evidence that solutions to a great variety of problems from many different fields can be found by genetically breeding populations of computer programs. Genetic Programming contains a great many worked examples and includes a sample computer code that will allow readers to run their own programs.In getting computers to solve problems without being explicitly programmed, Koza stresses two points: that seemingly different problems from a variety of fields can be reformulated as problems of program induction, and that the recently developed genetic programming paradigm provides a way to search the space of possible computer programs for a highly fit individual computer program to solve the problems of program induction. Good programs are found by evolving them in a computer against a fitness measure instead of by sitting down and writing them.

 

Contents

Introduction and Overview
1
algorithm operating on fixedlength character strings and variations of the con
4
Pervasiveness of the Problem of Program Induction
9
Introduction to Genetic Algorithms
17
wide variety of problems from a wide variety of fields These chapters are divided
20
The Representation Problem for Genetic Algorithms
63
Overview of Genetic Programming
73
Detailed Description of Genetic Programming
79
Evolution of Building Blocks
527
Evolution of Hierarchies of Building Blocks
553
evolution of hierarchical building blocks by means of hierarchical automatic
561
Parallelization of Genetic Programming
563
Ruggedness of Genetic Programming
569
Extraneous Variables and Functions
583
Operational Issues
597
Review of Genetic Programming
619

Four Introductory Examples of Genetic Programming
121
Amount of Processing Required to Solve a Problem
191
Nonrandomness of Genetic Programming
205
Symbolic RegressionErrorDriven Evolution
237
ControlCostDriven Evolution
289
Evolution of Emergent Behavior
329
Evolution of Subsumption
357
EntropyDriven Evolution
395
entropydriven evolutionchapter 14
417
Evolution of Strategy
419
CoEvolution
429
Evolution of Classification
439
Iteration Recursion and Setting
459
Evolution of Constrained Syntactic Structures
479
evolution of iteration and recursionchapter 18
512
Comparison with Other Paradigms
633
Spontaneous Emergence of SelfReplicating
643
sexuallyreproducing and selfimproving computer programs
652
Conclusions
695
ProblemSpecific Part of Simple LISP Code
705
Kernel of the Simple LISP Code
735
Embellishments to the Simple LISP Code
757
Streamlined Version of EVAL
765
Editor for Simplifying SExpressions
771
Testing the Simple LISP Code
777
TimeSaving Techniques
783
List of Special Functions
789
Index
805
Copyright

Common terms and phrases

About the author (1992)

John R. Koza is Consulting Associate Professor in the Computer Science Department at Stanford University.

Bibliographic information