Friday, January 28, 2005
Are competent learning classifier systems emerging?
Estimation of distribution algorithms (EDAs) have changed the way people approach to evolutionary algorithms. Recently, such approaches are slowly infiltrating in the learning classifier systems world.
Early efforts of Sierra, Jiménez, Inza, Larrañaga, and Muruzábal showed that such algorithms may also be used in genetics-based machine learning approaches. They build a simple Pittsburgh approach classifier based on EDAs. Recently, however, such approaches have hit the main stream of LCS, XCS.
The usage of EDAs can help addressing two major issues in XCS: (1) knowledge extraction and (2) structure identification. Knowledge extraction addresses the issue of mining problem knowledge from the final solution developed by XCS. The goal is to identify most important features in the problem and the dependencies among those features. The extracted knowledge may not only be used for further data mining, but may actually be re-fed into the system giving it further competence in solving problems in which dependent features, that is, building blocks, need to be processed effectively. A paper proposing to extract a feature dependency tree out of the developed rule-based problem representation of XCS may be found here.
Early efforts of Sierra, Jiménez, Inza, Larrañaga, and Muruzábal showed that such algorithms may also be used in genetics-based machine learning approaches. They build a simple Pittsburgh approach classifier based on EDAs. Recently, however, such approaches have hit the main stream of LCS, XCS.
The usage of EDAs can help addressing two major issues in XCS: (1) knowledge extraction and (2) structure identification. Knowledge extraction addresses the issue of mining problem knowledge from the final solution developed by XCS. The goal is to identify most important features in the problem and the dependencies among those features. The extracted knowledge may not only be used for further data mining, but may actually be re-fed into the system giving it further competence in solving problems in which dependent features, that is, building blocks, need to be processed effectively. A paper proposing to extract a feature dependency tree out of the developed rule-based problem representation of XCS may be found here.
