Title :
Partial functions in fitness-shared genetic programming
Author_Institution :
Sch. of Comput. Sci., Australian Defence Force Acad., Canberra, ACT, Australia
Abstract :
Investigates the use of partial functions and fitness sharing in genetic programming. Fitness sharing is applied to populations of either partial or total functions and the results are compared. Applications to two classes of problem are investigated: learning multiplexer definitions, and learning (recursive) list membership functions. In both cases, fitness sharing approaches outperform the use of raw fitness, by generating more accurate solutions with the same population parameters. On the list membership problem, variants using fitness sharing on populations of partial functions outperform variants using total functions, whereas populations of total functions give better performance on some variants of multiplexer problems
Keywords :
functions; genetic algorithms; learning (artificial intelligence); list processing; multiplexing equipment; software performance evaluation; accurate solutions; fitness sharing; genetic programming; multiplexer definition learning; partial functions; performance; population parameters; recursive list membership function learning; total functions; Application software; Australia; Computer science; Delay; Drives; Error analysis; Evolutionary computation; Genetic programming; Multiplexing; Shape;
Conference_Titel :
Evolutionary Computation, 2000. Proceedings of the 2000 Congress on
Conference_Location :
La Jolla, CA
Print_ISBN :
0-7803-6375-2
DOI :
10.1109/CEC.2000.870316