Accuracy-based Learning Classifier Systems:: Models, analysis and applications to classification tasks

被引:210
作者
Bernadó-Mansilla, E [1 ]
Garrell-Guiu, JM [1 ]
机构
[1] Ramon Llull Univ, Barcelona 08022, Spain
关键词
learning classifier systems; accuracy-based fitness; knowledge representation; learning complexity; generalization; data mining;
D O I
10.1162/106365603322365289
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, Learning Classifier Systems (LCS) and particularly XCS have arisen as promising methods for classification tasks and data ruining. This paper investigates two models of accuracy-based learning classifier systems oil different types of classification problems. Departing from XCS, we analyze the evolution of a complete action map as a knowledge representation. We propose an alternative, UCS, which evolves a best action map more efficiently. We also investigate how the fitness pressure guides the search towards accurate classifiers. While XCS bases fitness oil a reinforcement learning scheme, UCS defines fitness from a supervised learning scheme. We find significant differences in how the fitness pressure leads towards accuracy, and suggest the use of a supervised approach specially for multi-class problems and problems with unbalanced classes. We also investigate the complexity factors which arise ill each type of accuracy-based LCS. We provide a model on the learning complexity of LCS which is based oil the representative examples given to the system. The results and observations are also extended to a set of real world classification problems, where accuracy-based LCS are shown to perform competitively with respect to other learning algorithms. The work presents an extended analysis of accuracy-based LCS, gives insight into the Understanding of the LCS dynamics, and suggests open issues for further improvement of LCS on classification tasks.
引用
收藏
页码:209 / 238
页数:30
相关论文
共 38 条
[1]  
AHA DW, 1991, MACH LEARN, V6, P37, DOI 10.1007/BF00153759
[2]  
[Anonymous], FESTSCHRIFT HONOR JH
[3]  
Bernadó E, 2002, LECT NOTES ARTIF INT, V2321, P115
[4]  
BERNADOMANSILLA E, 2002, THESIS R LULL U BARC
[5]  
BERNADOMANSILLA E, 2001, LECT NOTES COMPUTER, V1993, P696
[6]  
Blake C., 1998, UCI Repository of Machine Learning Databases
[7]  
BONELLI P, 1990, 7 INT C MACH LEARN, P153
[8]  
Bull L., 2002, Parallel Problem Solving from Nature - PPSN VII. 7th International Conference. Proceedings (Lecture Notes in Computer Science Vol.2439), P568
[9]  
Butz M. V., 2001, Advances in Learning Classifier Systems. Third International Workshop, IWLCS 2000. Revised Papers (Lecture Notes in Artificial Intelligence Vol.1996), P253
[10]  
Butz M.V., 2001, P GENETIC EVOLUTIONA, P935