Bloat control and generalization pressure using the minimum description length principle for a pittsburgh approach learning classifier system

Authors:
Jaume Bacardit;Josep Maria Garrell
Affiliations:
Automated Scheduling, Optimisation and Planning research group, School of Computer Science and IT, University of Nottingham, Nottingham, UK;Intelligent Systems Research Group, Enginyeria i Arquitectura La Salle, Universitat Ramon Llull, Barcelona, Catalonia, Spain, Europe
Venue:
IWLCS'03-05 Proceedings of the 2003-2005 international conference on Learning classifier systems
Year:
2007

Citing 15
Cited 19

Instance-Based Learning Algorithms

Machine Learning
C4.5: programs for machine learning

C4.5: programs for machine learning
Genetic programming using a minimum description length principle

Advances in genetic programming
Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Applying MDL to learn best model granularity

Artificial Intelligence
Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence
Machine Learning

Machine Learning
Learning Decision Lists

Machine Learning
Lexicographic Parsimony Pressure

GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Accuracy-based learning classifier systems: models, analysis and applications to classification tasks

Evolutionary Computation
Classifier fitness based on accuracy

Evolutionary Computation
Flexible learning of problem solving heuristics through adaptive search

IJCAI'83 Proceedings of the Eighth international joint conference on Artificial intelligence - Volume 1
Learning concept classification rules using genetic algorithms

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
A study of cross-validation and bootstrap for accuracy estimation and model selection

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Evolving multiple discretizations with adaptive intervals for a Pittsburgh rule-based learning classifier system

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII

DXCS: an XCS system for distributed data mining

GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Data mining with a simulated annealing based fuzzy classification system

Pattern Recognition
Data mining with a simulated annealing based fuzzy classification system

Pattern Recognition
A new approach for multi-label classification based on default hierarchies and organizational learning

Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
Managing team-based problem solving with symbiotic bid-based genetic programming

Proceedings of the 10th annual conference on Genetic and evolutionary computation
Hierarchical evolution of linear regressors

Proceedings of the 10th annual conference on Genetic and evolutionary computation
Technology Extraction of Expert Operator Skills from Process Time Series Data

Learning Classifier Systems
On the appropriateness of evolutionary rule learning algorithms for malware detection

Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Performance evaluation of evolutionary algorithms in classification of biomedical datasets

Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Performance and efficiency of memetic pittsburgh learning classifier systems

Evolutionary Computation
Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: Experimental analysis of power

Information Sciences: an International Journal
Data mining in learning classifier systems: comparing XCS with GAssist

IWLCS'03-05 Proceedings of the 2003-2005 international conference on Learning classifier systems
Improving the performance of a pittsburgh learning classifier system using a default rule

IWLCS'03-05 Proceedings of the 2003-2005 international conference on Learning classifier systems
Using computational intelligence to identify performance bottlenecks in a computer system

PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part I
Genetics-based machine learning for rule induction: state of the art, taxonomy, and comparative study

IEEE Transactions on Evolutionary Computation
Random artificial incorporation of noise in a learning classifier system environment

Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Machine learning and agents

KES-AMSTA'11 Proceedings of the 5th KES international conference on Agent and multi-agent systems: technologies and applications
Clonal selection algorithm for classification

ICARIS'11 Proceedings of the 10th international conference on Artificial immune systems
An interpretable classification rule mining algorithm

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bloat control and generalization pressure are very important issues in the design of Pittsburgh Approach Learning Classifier Systems (LCS), in order to achieve simple and accurate solutions in a reasonable time. In this paper we propose a method to achieve these objectives based on the Minimum Description Length (MDL) principle. This principle is a metric which combines in a smart way the accuracy and the complexity of a theory (rule set, instance set, etc.). An extensive comparison with our previous generalization pressure method across several domains and using two knowledge representations has been done. The test show that the MDL based size control method is a good and robust choice.