Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, pp. 84–214. John Wiley and Sons, Chichester (2001)
Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P.: From data mining to knowledge discovery: an overview. In: Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P., Uthurusamy, R. (eds.) Advances in Knowledge Discovery and Data Mining, pp. 1–34. AAAI Press, Menlo Park (1996)
Flach, P.A., Lavrac, N.: The role of Feature Construction in Inductive Rule Learning. In: ICML, pp. 1–11 (2000)
Guyon, I., Elisseeff, A.: An Introduction to Variable and Feature Selection. Machine Learning, 1157–1182 (2003)
Kramer, S.: Demand-Driven Construction of Structural Features in ILP. In: Rouveirol, C., Sebag, M. (eds.) ILP 2001. LNCS (LNAI), vol. 2157, pp. 132–141. Springer, Heidelberg (2001)
Kohavi, R., John, G.H.: Wrappers for Feature Subset Selection. Artificial Intelligence 97(1–2), 273–324 (1997)
Kudenko, D., Hirsh, H.: Feature Generation for Sequence Categorization. American Association for Artificial Intelligence, 733–738 (1998)
Lago-Fernández, L.F., Corbacho, F.J.: Optimal Extraction of Hidden Causes. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 631–636. Springer, Heidelberg (2002)
Levine, D.: Users Guide to the PGAPack Parallel Genetic Algorithm Library. T.R.ANL-95/18 (1996)
Pagallo, G.: Boolean Feature Discovery in Empirical Learning. Machine Learning 5(1), 71–99 (1990)
Prechelt, L.: Proben1: A set of Neural Network Benchmark Problems and Benchmarking Rules. Tech. Rep. 21/94, Fakultät für Informatik, Univ. Karlsruhe, Karlsruhe, Germany (1994)
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers Inc., San Francisco (1992)
Ragavan, H., Rendell, M.: Lookahead Feature Construction for Learning Hard Concepts. In: ICML, pp. 252–259 (1993)
Rennie, J.D.M., Jaakkola, T.: Automatic Feature Induction for Text Classification. MIT Artificial Intelligence Laboratory Abstract Book (2002)
Sierra, A., Macías, J.A., Corbacho, F.: Evolution of Functional Link Networks. IEEE Trans. Evol. Comp. 5(1), 54–65 (2001)
Utgoff, P.E., Precup, D.: Constructive Function Approximation. In: Liu, H., Motoda, H. (eds.) Feature Extraction, Construction and Selection: a Data Mining Perspective, Boston, pp. 219–235. Kluwer Academic, Dordrecht (1998)
Vapnik, V.N.: Statistical Learning Theory. John Wiley and Sons, Chichester (1998)
Zucker, J.D., Ganascia, J.G.: Representation Changes for Efficient Learning in Structural Domains. In: ICML, pp. 543–551 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
del Valle, M., Sánchez, B., Lago-Fernández, L.F., Corbacho, F.J. (2005). Feature Discovery in Classification Problems. In: Famili, A.F., Kok, J.N., Peña, J.M., Siebes, A., Feelders, A. (eds) Advances in Intelligent Data Analysis VI. IDA 2005. Lecture Notes in Computer Science, vol 3646. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11552253_44
Download citation
DOI: https://doi.org/10.1007/11552253_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28795-7
Online ISBN: 978-3-540-31926-9
eBook Packages: Computer ScienceComputer Science (R0)