Routine human-competitive machine intelligence by means of genetic programming

John R. Koza; Matthew J. Streeter; Martin Keane

doi:10.1117/12.512613

30 December 2003 Routine human-competitive machine intelligence by means of genetic programming

John R. Koza, Matthew J. Streeter, Martin Keane

Author Affiliations +

Proceedings Volume 5200, Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation VI; (2003) https://doi.org/10.1117/12.512613
Event: Optical Science and Technology, SPIE's 48th Annual Meeting, 2003, San Diego, California, United States

Abstract

Genetic programming is a systematic method for getting computers to automatically solve a problem. Genetic programming starts from a high-level statement of what needs to be done and automatically creates a computer program to solve the problem. The paper demonstrates that genetic programming (1) now routinely delivers high-return human-competitive machine intelligence; (2) is an automated invention machine; (3) can automatically create a general solution to a problem in the form of a parameterized topology; and (4) has delivered a progression of qualitatively more substantial results in synchrony with five approximately order-of-magnitude increases in the expenditure of computer time. Recent results involving the automatic synthesis of the topology and sizing of analog electrical circuits and controllers demonstrate these points.

Citation Download Citation

John R. Koza, Matthew J. Streeter, and Martin Keane "Routine human-competitive machine intelligence by means of genetic programming", Proc. SPIE 5200, Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation VI, (30 December 2003); https://doi.org/10.1117/12.512613

Access the abstract

PROCEEDINGS
15 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

CITATIONS

Cited by 51 scholarly publications.

Explore citations on Lens.org

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Computer programming

Genetics

Patents

Computing systems

Analog electronics

Capacitors

Transistors

Show All Keywords

RELATED CONTENT

SRAM-based in-memory-computing for AI edge devices
Proceedings of SPIE (March 07 2022)

Highly efficient neuromorphic computing systems with emerging nonvolatile memories
Proceedings of SPIE (March 23 2020)

Automatic generation of multipath algorithms in the cellular nonlinear network
Proceedings of SPIE (April 04 2001)

Developing an Expert Ship Message Interpreter Theoretical and Practical Conclusions
Proceedings of SPIE (April 05 1985)

Review of field-programmable analog arrays
Proceedings of SPIE (October 21 1996)

Expert Systems Application In Manufacturing
Proceedings of SPIE (May 11 1987)

Applications Of Artificial Intelligence To Computer-Aided Lens Design
Proceedings of SPIE (June 10 1987)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years