Learning Classifier Systems: 5th International Workshop, IWLCS 2002, Granada, Spain, September 7-8, 2002, Revised Papers / Edition 1

by Pier Luca Lanzi, Stewart W. Wilson, Wolfgang Stolzmann

Overview

The 5th International Workshop on Learning Classifier Systems (IWLCS2002) was held September 7–8, 2002, in Granada, Spain, during the 7th International Conference on Parallel Problem Solving from Nature (PPSN VII). We have included in this volume revised and extended versions of the papers presented at the workshop. In the first paper, Browne introduces a new model of learning classifier system, iLCS, and tests it on the Wisconsin Breast Cancer classification problem. Dixon et al. present an algorithm for reducing the solutions evolved by the classifier system XCS, so as to produce a small set of readily understandable rules. Enee and Barbaroux take a close look at Pittsburgh-style classifier systems, focusing on the multi-agent problem known as El-farol. Holmes and Bilker investigate the effect that various types of missing data have on the classification performance of learning classifier systems. The two papers by Kovacs deal with an important theoretical issue in learning classifier systems: the use of accuracy-based—tness as opposed to the more traditional strength-based—tness. In the first paper, Kovacs introduces a strength-based version of XCS, called SB-XCS. The original XCS and the new SB-XCS are compared in the second paper, where - vacs discusses the different classes of solutions that XCS and SB-XCS tend to evolve.

Product Details

ISBN-13:	9783540205449
Publisher:	Springer Berlin Heidelberg
Publication date:	01/22/2004
Series:	Lecture Notes in Computer Science , #2661
Edition description:	2003
Pages:	233
Product dimensions:	6.10(w) x 9.17(h) x 0.36(d)

Table of Contents

Balancing Specificity and Generality in a Panmictic-Based Rule-Discovery Learning Classifier System.- A Ruleset Reduction Algorithm for the XCS Learning Classifier System.- Adapted Pittsburgh-Style Classifier-System: Case-Study.- The Effect of Missing Data on Learning Classifier System Learning Rate and Classification Performance.- XCS’s Strength-Based Twin: Part I.- XCS’s Strength-Based Twin: Part II.- Further Comparison between ATNoSFERES and XCSM.- Accuracy, Parsimony, and Generality in Evolutionary Learning Systems via Multiobjective Selection.- Anticipatory Classifier System Using Behavioral Sequences in Non-Markov Environments.- Mapping Artificial Immune Systems into Learning Classifier Systems.- The 2003 Learning Classifier Systems Bibliography.