Boolean Feature Discovery in Empirical Learning
Machine Learning
C4.5: programs for machine learning
C4.5: programs for machine learning
From data mining to knowledge discovery: an overview
Advances in knowledge discovery and data mining
Wrappers for feature subset selection
Artificial Intelligence - Special issue on relevance
Feature generation for sequence categorization
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Optimal Extraction of Hidden Causes
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Demand-Driven Construction of Structural Features in ILP
ILP '01 Proceedings of the 11th International Conference on Inductive Logic Programming
An introduction to variable and feature selection
The Journal of Machine Learning Research
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Evolution of functional link networks
IEEE Transactions on Evolutionary Computation
Evolutionary search of optimal features
IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Hi-index | 0.00 |
In most problems of Knowledge Discovery the human analyst previously constructs a new set of features, derived from the initial problem input attributes, based on a priori knowledge of the problem structure. These different features are constructed from different transformations which must be selected by the analyst. This paper provides a first step towards a methodology that allows the search for near-optimal representations in classification problems by allowing the automatic selection and composition of feature transformations from an initial set of basis functions. In many cases, the original representation for the problem data is not the most appropriate, and the search for a new representation space that is closer to the structure of the problem to be solved is critical for the successful solution of the problem. On the other hand, once this optimal representation is found, most of the problems may be solved by a linear classification method. As a proof of concept we present two classification problems where the class distributions have a very intricate overlap on the space of original attributes. For these problems, the proposed methodology is able to construct representations based on function compositions from the trigonometric and polynomial bases that provide a solution where some of the classical learning methods, e.g. multilayer perceptrons and decision trees, fail. The methodology consists of a discrete search within the space of compositions of the basis functions and a linear mapping performed by a Fisher discriminant. We play special emphasis on the first part. Finding the optimal composition of basis functions is a difficult problem because of its nongradient nature and the large number of possible combinations. We rely on the global search capabilities of a genetic algorithm to scan the space of function compositions.