Genetic Programming III
Darwinian Invention and Problem Solving
- 1st Edition - April 30, 1999
- Latest edition
- Authors: John R. Koza, Forrest H. Bennett, David Andre, Martin A. Keane
- Language: English
Genetic programming is a method for getting a computer to solve a problem by telling it what needs to be done instead of how to do it. Koza, Bennett, Andre, and Keane present ge… Read more
Purchase options
World Book Day celebration
Where learning shapes lives
Up to 25% off trusted resources that support research, study, and discovery.
Description
Description
Genetic programming is a method for getting a computer to solve a problem by telling it what needs to be done instead of how to do it. Koza, Bennett, Andre, and Keane present genetically evolved solutions to dozens of problems of design, optimal control, classification, system identification, function learning, and computational molecular biology. Among the solutions are 14 results competitive with human-produced results, including 10 rediscoveries of previously patented inventions.
Researchers in artificial intelligence, machine learning, evolutionary computation, and genetic algorithms will find this an essential reference to the most recent and most important results in the rapidly growing field of genetic programming.
Key features
Key features
- Explains how the success of genetic programming arises from seven fundamental differences distinguishing it from conventional approaches to artificial intelligence and machine learning
- Describes how genetic programming uses architecture-altering operations to make on-the-fly decisions on whether to use subroutines, loops, recursions, and memory
- Demonstrates that genetic programming possesses 16 attributes that can reasonably be expected of a system for automatically creating computer programs
- Presents the general-purpose Genetic Programming Problem Solver
- Focuses on the previously unsolved problem of analog circuit synthesis, presenting genetically evolved filters, amplifiers, computational circuits, a robot controller circuit, source identification circuits, a temperature-measuring circuit, a voltage reference circuit, and more
- Introduces evolvable hardware in the form of field-programmable gate arrays
- Includes an introduction to genetic programming for the uninitiated
Readership
Readership
AI researchers and engineers involved with circuit design
Table of contents
Table of contents
I. Introduction
1.Introduction
II. Background
2.Background
III. Architecture-Altering Operations
3.Previous Methods of Determining the Architecture of a Multi-Part Program
4. On the Origin of New Functions
5.Architecture-Altering Operations for Subroutines
6.Automatically Defined Iterations
7.Automatically Defined Loops
8.Automatically Defined Recursion
9.Automatically Defined Storage
10.Self-Organization of Hierarchies and Program Architecture
11.Rotating the Tires on an Automobile
12.Boolean Parity Problem using Architecture-Altering Operations for Subroutines
13.Time-Optimal Robot Control Problem using Architecture-Altering Operations for Subroutines
14.Multi-Agent Problem using Architecture-Altering Operations for Subroutines
15.Digit Recognition Problem using Architecture-Altering Operations for Subroutines
16.Transmembrane Segment Identification Problem using Architecture-Altering Operations for Subroutines
17.Transmembrane Segment Identification Problem using Architecture-Altering Operations for Iterations
18.Fibonacci Sequence
19.Cart Centering
IV. Genetic Programming Problem Solver (GPPS)
20.Elements of GPPS 1.0
21.Three Problems Illustrating GPPS 1.0
22.Elements of GPPS 2.0
23.Six Problems Illustrating GPPS 2.0
24.Previous Work on Automated Analog Circuit Synthesis
V. Automated Synthesis of Analog Electrical Circuits
25.Synthesis of a Lowpass Filter
26.Synthesis of a Highpass Filter
27.Synthesis of a Lowpass Filter Using Automatically Defined Functions
28.Synthesis of a Lowpass Filter Using Architecture-Altering Operations
29.Embryos and Test Fixtures
30.Synthesis of a Lowpass Filter Using Automatically Defined Copy
31.Synthesis of an Asymmetric Bandpass Filter
32.Synthesis of a Two-Band Crossover (Woofer-Tweeter) Filter
33.Synthesis of a Two-Band Crossover (Woofer-Tweeter) Filter Using Architecture-Altering Operations
34.Synthesis of a Three-Band Crossover (Woofer-Midrange-Tweeter) Filter
35.Synthesis of a Double Bandpass Filter Using Subcircuits
36.Synthesis of a Double Bandpass Filter Using Architecture-Altering Operations
37.Synthesis of Butterworth, Chebychev, and Elliptic Filters
38.Synthesis of a Three-Way Source Identification Circuit
39.Synthesis of a Source Identification Circuit with a Changing Number of Sources
40.Lowpass Filter with Parsimony
41.Complete Repertoire of Circuit-Constructing Functions
42.Synthesis of a 10 dB Amplifier Using Transistors
43.Synthesis of a 40 dB Amplifier
44.Synthesis of a 60 dB Amplifier
45.Synthesis of a 96 dB Amplifier with Architecture-Altering Operations
46.Synthesis of an Amplifier with a High Power Supply Rejection Ratio
47.Synthesis of Computational Circuits
48.Synthesis of a Real-Time Robot Controller Circuit with Architecture-Altering Operations
49.Synthesis of a Temperature-Sensing Circuit
50.Synthesis of a Voltage Reference Circuit
51.Synthesis of a MOSFET Circuit
52.Constraints Involving Subcircuits or Topologies
53.Minimal Embryo
54.Comparative Experiments Involving the Lowpass Filter
55.Comparative Experiments Involving the Lowpass Filter and the Automatically Defined Copy
56.The Role of Crossover in Genetic Programming
VI. Evolvable Hardware
57.Evolvable Hardware and Rapidly Reconfigurable Field-Programmable Gate Arrays
VII. Discovery of Cellular Automata Rules
58.Discovery of a Cellular Automata Rule for the Majority Classification Problem
VIII. Discovery of Motifs and Programmatic Motifs for Molecular Biology
59.Automatic Discovery of Protein Motifs
60.Programmatic Motifs and the Cellular Location Problem
IX. Parallelization and Implementation Issues
61.Computer Time
62.Parallelization of Genetic Programming
63.Implementation Issues
X. Conclusion
64.Conclusion
1.Introduction
II. Background
2.Background
III. Architecture-Altering Operations
3.Previous Methods of Determining the Architecture of a Multi-Part Program
4. On the Origin of New Functions
5.Architecture-Altering Operations for Subroutines
6.Automatically Defined Iterations
7.Automatically Defined Loops
8.Automatically Defined Recursion
9.Automatically Defined Storage
10.Self-Organization of Hierarchies and Program Architecture
11.Rotating the Tires on an Automobile
12.Boolean Parity Problem using Architecture-Altering Operations for Subroutines
13.Time-Optimal Robot Control Problem using Architecture-Altering Operations for Subroutines
14.Multi-Agent Problem using Architecture-Altering Operations for Subroutines
15.Digit Recognition Problem using Architecture-Altering Operations for Subroutines
16.Transmembrane Segment Identification Problem using Architecture-Altering Operations for Subroutines
17.Transmembrane Segment Identification Problem using Architecture-Altering Operations for Iterations
18.Fibonacci Sequence
19.Cart Centering
IV. Genetic Programming Problem Solver (GPPS)
20.Elements of GPPS 1.0
21.Three Problems Illustrating GPPS 1.0
22.Elements of GPPS 2.0
23.Six Problems Illustrating GPPS 2.0
24.Previous Work on Automated Analog Circuit Synthesis
V. Automated Synthesis of Analog Electrical Circuits
25.Synthesis of a Lowpass Filter
26.Synthesis of a Highpass Filter
27.Synthesis of a Lowpass Filter Using Automatically Defined Functions
28.Synthesis of a Lowpass Filter Using Architecture-Altering Operations
29.Embryos and Test Fixtures
30.Synthesis of a Lowpass Filter Using Automatically Defined Copy
31.Synthesis of an Asymmetric Bandpass Filter
32.Synthesis of a Two-Band Crossover (Woofer-Tweeter) Filter
33.Synthesis of a Two-Band Crossover (Woofer-Tweeter) Filter Using Architecture-Altering Operations
34.Synthesis of a Three-Band Crossover (Woofer-Midrange-Tweeter) Filter
35.Synthesis of a Double Bandpass Filter Using Subcircuits
36.Synthesis of a Double Bandpass Filter Using Architecture-Altering Operations
37.Synthesis of Butterworth, Chebychev, and Elliptic Filters
38.Synthesis of a Three-Way Source Identification Circuit
39.Synthesis of a Source Identification Circuit with a Changing Number of Sources
40.Lowpass Filter with Parsimony
41.Complete Repertoire of Circuit-Constructing Functions
42.Synthesis of a 10 dB Amplifier Using Transistors
43.Synthesis of a 40 dB Amplifier
44.Synthesis of a 60 dB Amplifier
45.Synthesis of a 96 dB Amplifier with Architecture-Altering Operations
46.Synthesis of an Amplifier with a High Power Supply Rejection Ratio
47.Synthesis of Computational Circuits
48.Synthesis of a Real-Time Robot Controller Circuit with Architecture-Altering Operations
49.Synthesis of a Temperature-Sensing Circuit
50.Synthesis of a Voltage Reference Circuit
51.Synthesis of a MOSFET Circuit
52.Constraints Involving Subcircuits or Topologies
53.Minimal Embryo
54.Comparative Experiments Involving the Lowpass Filter
55.Comparative Experiments Involving the Lowpass Filter and the Automatically Defined Copy
56.The Role of Crossover in Genetic Programming
VI. Evolvable Hardware
57.Evolvable Hardware and Rapidly Reconfigurable Field-Programmable Gate Arrays
VII. Discovery of Cellular Automata Rules
58.Discovery of a Cellular Automata Rule for the Majority Classification Problem
VIII. Discovery of Motifs and Programmatic Motifs for Molecular Biology
59.Automatic Discovery of Protein Motifs
60.Programmatic Motifs and the Cellular Location Problem
IX. Parallelization and Implementation Issues
61.Computer Time
62.Parallelization of Genetic Programming
63.Implementation Issues
X. Conclusion
64.Conclusion
Review quotes
Review quotes
"Koza, Bennett, Andre, and Keane's evolutionary algorithm builds more complex and useful structures than the other approaches to computer learning that I have seen."—John McCarthy, Stanford University
"John Koza and colleagues have demonstrated that genetic programming can be used to search highly discontinuous spaces and thereby find amazing solutions to practical engineering problems."—Bernard Widrow, Stanford University
"In this impressive volume, the authors demonstrate that genetic programming is more than an intriguing idea-it is a practical synthesis method for solving hard problems."—Nils J. Nilsson, Stanford University
"Through careful experiment, keen algorithmic intuition, and relentless application the authors deliver important results that rival those achieved by human designers. All readers in genetic and evolutionary computation and the related fields of artificial life, agents, and adaptive behavior will want this volume in their collections."—David E. Goldberg, University of Illinois at Urbana-Champaign
"John Koza and his coauthors continue their relentless pursuit of a holy grail
in computer science: automatic programming."—Moshe Sipper, Swiss Federal Institute of Technology (EPFL), Lausanne
"John Koza and colleagues have demonstrated that genetic programming can be used to search highly discontinuous spaces and thereby find amazing solutions to practical engineering problems."—Bernard Widrow, Stanford University
"In this impressive volume, the authors demonstrate that genetic programming is more than an intriguing idea-it is a practical synthesis method for solving hard problems."—Nils J. Nilsson, Stanford University
"Through careful experiment, keen algorithmic intuition, and relentless application the authors deliver important results that rival those achieved by human designers. All readers in genetic and evolutionary computation and the related fields of artificial life, agents, and adaptive behavior will want this volume in their collections."—David E. Goldberg, University of Illinois at Urbana-Champaign
"John Koza and his coauthors continue their relentless pursuit of a holy grail
in computer science: automatic programming."—Moshe Sipper, Swiss Federal Institute of Technology (EPFL), Lausanne
Product details
Product details
- Edition: 1
- Latest edition
- Published: May 11, 1999
- Language: English
About the authors
About the authors
JK
John R. Koza
John R. Koza is a consulting professor in the Section on Medical Informatics, Department of Medicine, School of Medicine at Stanford University. Forrest H Bennett III is chief scientist of Genetic Programming Inc., Los Altos, California. David Andre is a Ph.D. student in the Computer Science Division at the University of California at Berkeley.
MK
Martin A. Keane
Martin A. Keane is chief scientist of Econometrics, Inc., Chicago. Scott Brave is a research assistant in the Tangible Media Group at the MIT Media Laboratory.