Time space tradeoffs in GA based feature selection for workload characterization

作者: Dan E. Tamir , Clara Novoa , Daniel Lowell

DOI: 10.1007/978-3-642-13025-0_66

关键词:

摘要: This paper reports the results of a research effort that explores time/space tradeoffs inherent to genetic algorithms (GA). The study analyzes redundancy in GA search space and lays out schema for efficient utilization record keeping form cache minimize redundancy. application used evaluation procedure is feature selection computer workload characterization. experimental demonstrate utility domain, show significant reduction execution time with virtually same solution quality.

参考文章(28)
Toniann Pitassi, Philipp Hertel, An Exponential Time/Space Speedup For Resolution Electronic Colloquium on Computational Complexity. ,vol. 14, ,(2007)
Next-Generation Applied Intelligence Lecture Notes in Computer Science. ,vol. 5579, ,(2009) , 10.1007/978-3-642-02568-6
David Allen, Adnan Darwiche, Optimal time-space tradeoff in probabilistic inference international joint conference on artificial intelligence. pp. 969- 975 ,(2003) , 10.1007/978-3-540-39879-0_3
Eunice E. Santos, Eugene Santos, Cache Diversity in Genetic Algorithm Design the florida ai research society. pp. 107- 111 ,(2000)
Yue Luo, A. Joshi, A. Phansalkar, L. John, J. Ghosh, Analyzing and improving clustering based sampling for microprocessor simulation symposium on computer architecture and high performance computing. pp. 193- 200 ,(2005) , 10.1109/CAHPC.2005.11
Narendra, Fukunaga, A Branch and Bound Algorithm for Feature Subset Selection IEEE Transactions on Computers. ,vol. 26, pp. 917- 922 ,(1977) , 10.1109/TC.1977.1674939
David Karhi, Dan E. Tamir, Caching in the TSP Search Space international conference industrial engineering other applications applied intelligent systems. pp. 221- 230 ,(2009) , 10.1007/978-3-642-02568-6_23
Rafael Bello, Amilkar Puris, Ann Nowe, Yailen Martínez, María M. García, Two Step Ant Colony System to Solve the Feature Selection Problem Lecture Notes in Computer Science. pp. 588- 596 ,(2006) , 10.1007/11892755_61