Human-competitive machine invention by means of genetic programming
Author:
- 12 June 2008
- journal article
- research article
- Published by Cambridge University Press (CUP) in Artificial Intelligence for Engineering Design, Analysis and Manufacturing
- Vol. 22 (3) , 185-193
Abstract
Genetic programming is a systematic method for getting computers to automatically solve problems. Genetic programming uses the Darwinian principle of natural selection and analogs of recombination (crossover), mutation, gene duplication, gene deletion, and certain mechanisms of developmental biology to progressively breed, over a series of many generations, an improved population of candidate solutions to a problem. This paper makes the points that genetic programming now routinely delivers human-competitive machine intelligence for problems of automated design and can serve as an automated invention machine.Keywords
This publication has 18 references indexed in Scilit:
- Undirected Training of Run Transferable Libraries2005
- Evolving InventionsScientific American, 2003
- Evolving Team Darwin United1999
- Reuse, parameterized reuse, and hierarchical reuse of substructures in evolving electrical circuits using genetic programming1997
- Morphogenesis for evolvable systems1996
- On Genetic Programming of Fuzzy Rule-Based Systems for Intelligent ControlIntelligent Automation and Soft Computing, 1996
- Automated Design of Both the Topology and Sizing of Analog Electrical Circuits Using Genetic Programming1996
- Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin EffectEvolutionary Computation, 1993
- COGNITIVE SYSTEMS BASED ON ADAPTIVE ALGORITHMS11Research reported in this paper was supported in part by the National Science Foundation under grant DCR 71-01997 and by the Horace H. Rackham School of Graduate Studies under grant 387156.1978
- I.—COMPUTING MACHINERY AND INTELLIGENCEMind, 1950