This article addresses the issues of colour classification and collision detection asthey occur in the legged league robot soccer environment of RoboCup. We show how the method of one-class classification with support vectormachines (SVMs) can be applied to solve these tasks satisfactorily usingthe limited hardware capacity of the prescribed Sony AIBO quadruped robots. The experimental evaluation shows an improvement over our previous methods of ellipse fitting for colour classification and the statistical approach used for collision detection.

We attempt to understand visual classification in humans using both psychophysical andmachine learning techniques. Frontal views of human faces were used for a gender classification task. Human subjects classified thefaces and their gender judgment, reaction time and confidence rating were recorded. Several hyperplane learning algorithms were used on the same classification task using the Principal Components of the texture and shape representation of the faces. The classification performance ofthe learning algorithms was estimated using the face database with the true gender of the faces as labels, and also with the gender estimated bythe subjects.

We propose a novel method of dimensionality reduction for supervised learning. Given a regression or classification problem in which we wish to predict a variable Y from an explanatory vector X, we treat the problem ofdimensionality reduction as that of finding a low-dimensional "effective subspace"of X which retains the statistical relationship between X and Y . We show that this problem can be formulated in terms of conditional independence. To turn this formulation into an optimization problem, we characterize the notion of conditional independence using covariance operators on reproducing kernel Hilbert spaces; this allows us to derive a contrast function for estimation of the effective subspace. Unlike manyconventional methods, the proposed method requires neither assumptions on the marginal distribution of X, nor a parametric model of the conditional distribution of Y .

We propose an information-theoretic clustering approach that incorporates a pre-known partition of the data, aiming to identify common clusters that cut across the given partition. In the standard clustering setting the formation of clusters is guided by a single source of feature information. The newly utilized pre-partition factor introduces an additional bias that counterbalances the impact of the features whenever they become correlated with this known partition. The resulting algorithmic framework was applied successfully to synthetic data, as well as to identifying text-based cross-religion correspondences.

A key issue in supervised protein classification is the representation of input sequencesof amino acids. Recent work using string kernels for protein datahas achieved state-of-the-art classification performance. However, suchrepresentations are based only on labeled data -- examples with known 3D structures, organized into structural classes -- while in practice, unlabeled data is far more plentiful. In this work, we develop simpleand scalable cluster kernel techniques for incorporating unlabeled datainto the representation of protein sequences. We show that our methods greatly improve the classification performance of string kernels andoutperform standard approaches for using unlabeled data, such as adding close homologs of the positive examples to the training data. We achieve equal or superior performance to previously presented cluster kernel methods while achieving far greater computational efficiency.

Gradient-following learning methods can encounter problems of implementation inmany applications, and stochastic variants are frequently used to overcome these difficulties. We derive quantitative learning curves for three online training methods used with a linear perceptron: direct gradient descent, node perturbation, and weight perturbation. The maximum learning rate for the stochastic methods scales inversely with the first power of the dimensionality of the noise injected into the system; withsufficiently small learning rate, all three methods give identical learning curves. These results suggest guidelines for when these stochastic methods will be limited in their utility, and considerations for architectures in which they will be effective.

Many classification algorithms, including the support vector machine, boosting and logistic regression, can be viewed as minimum contrast methods that minimize a convex surrogate of the 0-1 loss function. We characterize the statistical consequences of using such a surrogate by providing ageneral quantitative relationship between the risk as assessed using the 0-1 loss and the risk as assessed using any nonnegative surrogate loss function. We show that this relationship gives nontrivial bounds under theweakest possible condition on the loss function--that it satisfy a pointwise form of Fisher consistency for classification. The relationship is based on a variational transformation of the loss function that is easy to compute in many applications. We also present a refined version of this result in the case of low noise. Finally, we present applications of our results to the estimation of convergence rates in the general setting of function classes that are scaled hulls of a finite-dimensional base class.

Computer animated agents and robots bring a social dimension to human computerinteraction and force us to think in new ways about how computers could be used in daily life. Face to face communication is a real-time process operating at a time scale of less than a second. In this paper we present progress on a perceptual primitive to automatically detect frontal faces in the video stream and code them with respect to 7 dimensions in real time: neutral, anger, disgust, fear, joy, sadness, surprise. Theface finder employs a cascade of feature detectors trained with boosting techniques [13, 2]. The expression recognizer employs a novel combination of Adaboost and SVM's. The generalization performance to new subjects for a 7-way forced choice was 93.3% and 97% correct on two publicly available datasets.

We present a new method for calculating approximate marginals for probability distributions defined by graphs with cycles, based on a Gaussian entropybound combined with a semidefinite outer bound on the marginal polytope. This combination leads to a log-determinant maximization problemthat can be solved by efficient interior point methods [8]. As with the Bethe approximation and its generalizations [12], the optimizing arguments of this problem can be taken as approximations to the exact marginals. In contrast to Bethe/Kikuchi approaches, our variational problemis strictly convex and so has a unique global optimum. An additional desirable feature is that the value of the optimal solution is guaranteed to provide an upper bound on the log partition function. In experimental trials, the performance of the log-determinant relaxation is comparable to or better than the sum-product algorithm, and by a substantial marginfor certain problem classes. Finally, the zero-temperature limit of our log-determinant relaxation recovers a class of well-known semidefinite relaxations for integer programming [e.g., 3].

We propose a method for sequential Bayesian kernel regression.