Minimal Achievable Error in the LED problem

This paper presents a theoretical model to predict the minimal achievable error, given a noise ratio ǫ, in the LED data set problem. The motivation for developing this theoretical model is to understand and explain some of the results that different systems achieve when they solve the LED problem. Moreover, given a new learning algorithm that solves the LED problem, we can now bound its optimal generalization accuracy.

[1]  Stephen F. Smith,et al.  Flexible Learning of Problem Solving Heuristics Through Adaptive Search , 1983, IJCAI.

[2]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[3]  John H. Holland,et al.  Escaping brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systems , 1995 .

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Larry J. Eshelman,et al.  Using Weighted Networks to Represent Classification Knowledge in Noisy Domains , 1988, ML.

[6]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[7]  Filippo Neri,et al.  Search-Intensive Concept Induction , 1995, Evolutionary Computation.

[8]  Stewart W. Wilson.  Classifier Fitness Based on Accuracy , 1995, Evolutionary Computation.

[9]  Ian W. Flockhart.  GA-MINER : Parallel Data Mining with Hierarchical Genetic Algorithms Final Report , 1995 .

[10]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[11]  Pier Luca Lanzi,et al.  A Study of the Generalization Capabilities of XCS , 1997, ICGA.

[12]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[13]  T. Kovacs.  XCS Classifier System Reliably Evolves Accurate, Complete, and Minimal Representations for Boolean Functions , 1998 .

[14]  J. Ross Quinlan,et al.  Simplifying decision trees , 1987, Int. J. Hum. Comput. Stud..

[15]  Xavier Llorà,et al.  Inducing Partially-Defined Instances with Evolutionary Algorithms , 2001, ICML.

[16]  Martin V. Butz,et al.  How XCS evolves accurate classifiers , 2001 .

[17]  M. Pelikán,et al.  Analyzing the evolutionary pressures in XCS , 2001 .

[18]  David E. Goldberg,et al.  The Design of Innovation: Lessons from and for Competent Genetic Algorithms , 2002 .