Improving the evolutionary coding for machine learning tasks
作者： Jesus S. Aguilar-Ruiz , José C. Riquelme , Carmelo Del Valle
DOI:
关键词: Machine learning 、 Artificial intelligence 、 Coding (social sciences) 、 Evaluation function 、 Evolutionary algorithm 、 Genetic population 、 Decision rule 、 Computer science
摘要: The most influential factors in the quality of solutions found by an evolutionary algorithm are a correct coding search space and appropriate evaluation function potential solutions. for obtaining decision rules is approached, i.e., representation individuals genetic population. Two new methods encoding discrete continuous attributes presented. Our "natural coding" uses one gene per attribute (continuous or discrete) leading to reduction space. Genetic operators this approached natural formally described size analysed several databases from UCI machine learning repository.
us.es参考文章(18)
Miguel Toro, José Riquelme, Jesús Aguilar, Three geometric approaches for representing decision rules in a supervised learning system genetic and evolutionary computation conference. pp. 771- 771 ,(1999)
Miguel Toro, José C. Riquelme, Jesús S. Aguilar, Data set editing by ordered projection european conference on artificial intelligence. pp. 251- 255 ,(2000)
John H. Holland, Adaptation in natural and artificial systems ,(1992)
Steven L. Salzberg, Alberto Segre, Programs for Machine Learning ,(1994)
Jesús Aguilar, José Riqueltne, Miguel Toro, A Tool to Obtain a Hierarchical Qualitative Rules form Quantitative Data industrial and engineering applications of artificial intelligence and expert systems. pp. 336- 346 ,(1998) , 10.1007/3-540-64582-9_764
F. Herrera, M. Lozano, J.L. Verdegay, Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis Artificial Intelligence Review. ,vol. 12, pp. 265- 319 ,(1998) , 10.1023/A:1006504901164
Larry J. Eshelman, J. David Schaffer, Real-Coded Genetic Algorithms and Interval-Schemata foundations of genetic algorithms. ,vol. 2, pp. 187- 202 ,(1993) , 10.1016/B978-0-08-094832-4.50018-0
Keki B. Irani, Usama M. Fayyad, Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning international joint conference on artificial intelligence. ,vol. 2, pp. 1022- 1027 ,(1993)
Cezary Z. Janikow, A Knowledge-Intensive Genetic Algorithm for Supervised Learning Machine Learning. ,vol. 13, pp. 189- 228 ,(1993) , 10.1007/BF00993043
Kenneth A. De Jong, William M. Spears, Diana F. Gordon, Using Genetic Algorithms for Concept Learning Machine Learning. ,vol. 13, pp. 161- 188 ,(1993) , 10.1007/BF00993042