Geometric Decision Tree

In this paper, we present a new algorithm for learning oblique decision trees. Most of the current decision tree algorithms rely on impurity measures to assess the goodness of hyperplanes at each node while learning a decision tree in top-down fashion. These impurity measures do not properly capture the geometric structures in the data. Motivated by this, our algorithm uses a strategy for assessing the hyperplanes in such a way that the geometric structure in the data is taken into account. At each node of the decision tree, we find the clustering hyperplanes for both the classes and use their angle bisectors as the split rule at that node. We show through empirical studies that this idea leads to small decision trees and better performance. We also present some analysis to show that the angle bisectors of clustering hyperplanes that we use as the split rules at each node are solutions of an interesting optimization problem and hence argue that this is a principled method of learning a decision tree.

A new approach to the design of reinforcement schemes for learning automata

On introduit une nouvelle classe de schémas de renforcement des automates d'apprentissage utilisant les estimations des caractéristiques aléatoires de l'environnement. On montre que les algorithmes convergent en probabilité vers le choix optimal des actions. On présente les résultats de simulation et on suggère des applications à un environnement à plusieurs apprentissages

Noise tolerance under risk minimization

In this paper, we explore noise-tolerant learning of classifiers. We formulate the problem as follows. We assume that there is an unobservable training set that is noise free. The actual training set given to the learning algorithm is obtained from this ideal data set by corrupting the class label of each example. The probability that the class label of an example is corrupted is a function of the feature vector of the example. This would account for most kinds of noisy data one encounters in practice. We say that a learning method is noise tolerant if the classifiers learnt with noise-free data and with noisy data, both have the same classification accuracy on the noise-free data. In this paper, we analyze the noise-tolerance properties of risk minimization (under different loss functions). We show that risk minimization under 0-1 loss function has impressive noise-tolerance properties and that under squared error loss is tolerant only to uniform noise; risk minimization under other loss functions is not noise tolerant. We conclude this paper with some discussion on the implications of these theoretical results.

Coarse-to-fine vision-based localization by indexing scale-invariant features

This paper presents a novel coarse-to-fine global localization approach inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by scale-invariant transformation feature descriptors are used as natural landmarks. They are indexed into two databases: a location vector space model (LVSM) and a location database. The localization process consists of two stages: coarse localization and fine localization. Coarse localization from the LVSM is fast, but not accurate enough, whereas localization from the location database using a voting algorithm is relatively slow, but more accurate. The integration of coarse and fine stages makes fast and reliable localization possible. If necessary, the localization result can be verified by epipolar geometry between the representative view in the database and the view to be localized. In addition, the localization system recovers the position of the camera by essential matrix decomposition. The localization system has been tested in indoor and outdoor environments. The results show that our approach is efficient and reliable. © 2006 IEEE.

Refigurando monstros: a perspectiva parcial de Donna Haraway como crítica da ciência

Esta dissertação trata das relações de poder que marcam a produção científica ocidental moderna a partir da abordagem dos estudos sobre Gênero e Ciência da feminista historiadora da ciência estadunidense Donna Haraway. Esta autora propõe a concepção de toda a produção de conhecimento como pratica política, assumindo a perspectiva parcial como fundamento para uma ciência objetiva e apontando a perspectiva de objetividade calcada na ideia de imparcialidade como produtora de um tipo de saber que historicamente serviu como instrumento de dominação: o conhecimento que se propõe como universal. Em sua narrativa, o androcentrismo, o etnocentrismo, o racismo e as divisões de classe operam na conformação e nas transformações desta ciência a partir da construção de um sujeito privilegiado do conhecimento, o cientista, figura constituída a imagem e semelhança do homem branco ocidental independente. Meu recorte de sua obra são as reformulações dessas relações ao longo da historia da ciência ocidental moderna observadas por ela na emergência e nas produções de um conjunto especifico de disciplinas do campo das ciências naturais biológicas, fortemente marcadas pelas teorias e tecnologias da informação e da comunicação produzidas no campo da cibernética. Na construção de um discurso critico sobre os saberes / poderes hegemônicos, Haraway traz para a cena da ciência figuras monstruosas, entre elas o ciborgue, tanto como meio de revelar categorias culturais atuando na produção do conhecimento como para materializar novos significados para natureza, os corpos e as relações de diferença. Em conexão com esses monstros, refigurados em suas narrativas, a autora defende uma relação de conexão, e não de divisão, entre sujeito e objeto do saber.