Options
Improving evolvability of genetic parallel programming using dynamic sample weighting
Date Issued
2003
Publisher
Springer Berlin, Heidelberg
ISBN
9783540451105
9783540406037
ISSN
03029743
Citation
Cheang, Sin Man, Lee, Kin Hong & Leung, Kwong Sak (2003). Improving evolvability of genetic parallel programming using dynamic sample weighting. In Cantú-Paz, Erick, Foster, James A., Deb, Kalyanmoy, Davis, Lawrence David, Roy, Rajkumar, O'Reilly, Una-May, Beyer, Hans Georg, Standish, Russell, Kendall, Graham, Wilson, Stewart, Harman, Mark, Wegener, Joachim, Dasgupta, Dipankar, Potter, Mitch A., Schultz, Alan C., Dowsland, Kathryn A.. Jonoska, Natasha & Miller, Julian (Eds.). Genetic and Evolutionary Computation — GECCO 2003. GECCO 2003, Chicago, USA (1802-1803). Springer Berlin, Heidelberg.
Type
Conference Paper
Abstract
This paper investigates the sample weighting effect on Genetic Parallel Programming (GPP) that evolves parallel programs to solve the training samples captured directly from a real-world system. The distribution of these samples can be extremely biased. Standard GPP assigns equal weights to all samples. It slows down evolution because crowded regions of samples dominate the fitness evaluation and cause premature convergence. This paper compares the performance of four sample weighting (SW) methods, namely, Equal SW (ESW), Class-equal SW (CSW), Static SW (SSW) and Dynamic SW (DSW) on five training sets. Experimental results show that DSW is superior in performance on tested problems. © Springer-Verlag Berlin Heidelberg 2003.
Loading...
Availability at HKSYU Library
