%0 Conference Proceedings
%A Rocha, Anderson,
%A Papa, João Paulo,
%A Meira, Luis A. A.,
%@affiliation Institute of Computing, University of Campinas (UNICAMP), Brazil
%@affiliation Department of Computer Science, State University of São Paulo (UNESP), Brazil
%@affiliation Department of Science and Technology, Federal University of São Paulo (UNIFESP), Brazil
%T How Far You Can Get Using Machine Learning Black-Boxes
%B Conference on Graphics, Patterns and Images, 23 (SIBGRAPI)
%E Bellon, Olga,
%E Esperança, Claudio,
%8 Aug. 30 - Sep. 3, 2010
%J Los Alamitos
%I IEEE Computer Society
%K Learning Black-Boxes, Metrics Space, Pattern Analysis, Support Vector Machines, Optimum-Path Forest, Neural Networks, K-Nearest Neighbors.
%X Supervised Learning (SL) is a machine learning research area which aims at developing techniques able to take advantage from labeled training samples to make decisions over unseen examples. Recently, a lot of tools have been presented in order to perform machine learning in a more straightfor- ward and transparent manner. However, one problem that is increasingly present in most of the SL problems being solved is that, sometimes, researchers do not completely understand what supervised learning is and, more often than not, publish results using machine learning black-boxes. In this paper, we shed light over the use of machine learning black-boxes and show researchers how far they can get using these out-of-the- box solutions instead of going deeper into the machinery of the classifiers. Here, we focus on one aspect of classifiers namely the way they compare examples in the feature space and show how a simple knowledge about the classifiers machinery can lift the results way beyond out-of-the-box machine learning solutions.