Continuous Endpoint Data Mining with ExSTraCS: A Supervised Learning Classifier System

  title={Continuous Endpoint Data Mining with ExSTraCS: A Supervised Learning Classifier System},
  author={Ryan J. Urbanowicz and Niranjan Ramanand and Jason H. Moore},
  journal={Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation},
ExSTraCS is a powerful Michigan-style learning classifier system (LCS) that was developed for classification, prediction, modeling, and knowledge discovery in complex and/or heterogeneous supervised learning problems with clean or noisy signals. To date, ExSTraCS has been limited to problems with discrete endpoints (i.e. classes). Many real world problems, however, involve endpoints with continuous values (e.g. function approximation, or quantitative trait analyses). In some problems the goal… 
Problem Driven Machine Learning by Co-evolving Genetic Programming Trees and Rules in a Learning Classifier System
This paper hypothesizes that if an LCS population includes and co-evolves two disparate representations than the system can adapt the appropriate representation to best capture meaningful patterns of association, regardless of the complexity of that association, or the nature of the endpoint.
LCS-DIVE: An Automated Rule-based Machine Learning Visualization Pipeline for Characterizing Complex Associations in Classification
This work introduces the LCS Discovery and Visualization Environment (LCS-DIVE), an automated LCS model interpretation pipeline for complex biomedical classification that was evaluated over a diverse set of simulated genetic and benchmark datasets encoding a variety of complex multivariate associations.
Multilabel Classification with Weighted Labels Using Learning Classifier Systems
The Michigan style strength-based learning classifier system, which is a rule-based supervised learning algorithm, is extended to handle multi-label classification tasks and results show the ability of the model in learning multi-class and multi- label data with low confidence estimation error.
SupRB: A Supervised Rule-based Learning System for Continuous Problems
The SupRB learning system is proposed, a new Pittsburgh-style learning classifier system (LCS) for supervised learning on multi-dimensional continuous decision problems that is able to make an optimal choice as well as predict the quality of a choice in a given situation.
Multi-label Classification With Weighted Labels Using Learning Classifier Systems
In this work the Michigan style strength-based learning classifier system, which is a rule-based supervised learning algorithm, is extended by changing its action space representation to handle
Absumption and subsumption based learning classifier systems
The new LCS, termed Absumption Subsumption Classifier System (ASCS), successfully produces interpretable models for all the complex domains tested, whereas the non-optimal rules in existing techniques obscure the patterns.
Evolving genetic programming trees in a rule-based learning framework
This work demonstrates the capability of GP trees to be evolved within an LCS-algorithm framework with comparable performance to a set of standard GP frameworks and discusses how these results support the feasibility of a GP-LCS framework and next-step challenges to be addressed.
Two-Step Markov Update Algorithm for Accuracy-Based Learning Classifier Systems
A mathematical framework using discrete-time dynamical system theory to analyze the stability and convergence of the two-step Markov update scheme for the reinforcement component of XCS, a family of accuracybased learning classifier systems shows faster convergence, better steady-state training accuracy and less sensitivity to variations in learning rates.
An effective action covering for multi-label learning classifier systems: a graph-theoretic approach
A multi-label learning classifier system that leverages a structured representation for the labels through undirected graphs to utilize the label similarities when evolving rules, as well as a method to calculate ML prediction arrays.


An Extended Michigan-Style Learning Classifier System for Flexible Supervised Learning, Classification, and Data Mining
This work introduces ExSTraCS (Extended Supervised Tracking and Classifying System), as a promising platform to address the challenges of modeling complex patterns of association, systems biology, and ‘big data’ challenges using supervised learning and a Michigan-Style LCS architecture.
Instance-linked attribute tracking and feedback for michigan-style supervised learning classifier systems
This study introduces attribute tracking, a mechanism akin to memory, for supervised learning in M-LCSs, and introduces attribute feedback to the mutation and crossover mechanisms, which significantly improves test accuracy, efficient generalization, run time, and the power to discriminate between predictive and non-predictive attributes in the presence of heterogeneity.
ExSTraCS 2.0: description and evaluation of a scalable learning classifier system
Performance over a complex spectrum of simulated genetic datasets demonstrated that these new mechanisms dramatically improve nearly every performance metric on datasets with 20 attributes and made it possible for ExSTraCS to reliably scale up to perform on related 200 and 2000-attribute datasets.
Accuracy-Based Learning Classifier Systems: Models, Analysis and Applications to Classification Tasks
This paper investigates two models of accuracy-based learning classifier systems on different types of classification problems, and provides a model on the learning complexity of LCS which is based on the representative examples given to the system.
The application of michigan-style learning classifiersystems to address genetic heterogeneity and epistasisin association studies
This study explores an alternative strategy (Learning Classifier Systems (LCSs)) as a direct approach for the characterization, and modeling of disease in the presence of both GH and epistasis, providing proof of principle for the application of LCSs to the GH/epistasis problem, and laying the foundation for the development of an LCS algorithm specifically designed to address GH.
Learning classifier systems: a complete introduction, review, and roadmap
This paper aims to provide an accessible foundation for researchers of different backgrounds interested in selecting or developing their own LCS, including a simple yet thorough introduction, a historical review, and a roadmap of algorithmic components, emphasizing differences in alternative LCS implementations.
Rapid Rule Compaction Strategies for Global Knowledge Discovery in a Supervised Learning Classifier System
This work introduces and evaluates two new rule compaction strategies (QRC, PDRC) and a simple rule filtering method (QRF), and compares them to three existing methodologies, suggesting PDRC to be the most balanced approach trading a minimal loss in testing accuracy for significant gains or consistency in all other performance statistics.
Using Expert Knowledge to Guide Covering and Mutation in a Michigan Style Learning Classifier System to Detect Epistasis and Heterogeneity
This study demonstrates that expert knowledge can improve learning efficiency in the context of a Michigan-style LCS by being incorporated to guide learning towards regions of the problem domain most likely to be of interest.
Improving the scalability of rule-based evolutionary learning
A new representation motivated by observations that Bioinformatics and Systems Biology often give rise to very large-scale datasets that are noisy, ambiguous and usually described by a large number of attributes is presented, which is up to 2–3 times faster than state-of-the-art evolutionary learning representations designed specifically for efficiency purposes.
Fuzzy-UCS: A Michigan-Style Learning Fuzzy-Classifier System for Supervised Learning
Fuzzy-UCS is inspired by UCS, an on-line accuracy-based learning classifier system that introduces a linguistic representation of the rules with the aim of evolving more readable rule sets, while maintaining similar performance and generalization capabilities to those presented by UCS.