We start by noting that conditional independence X ⊥ Y |B⊤X does not necessarily imply the correlation between BX and Y is maximized. To see this, let X be a Gaussian random vairable with zero mean and diagonal covariance matrix. AssumeB is an identity matrix and Y = X = (BX) (elementwise square for a vectorial X). The conditional independence is obviously satisfied yet the correlation between ...

In our previous work we have shown that Mahalanobis kernels are useful for support vector classifiers both from generalization ability and model selection speed. In this paper we propose using Mahalanobis kernels for function approximation. We determine the covariance matrix for the Mahalanobis kernel using all the training data. Model selection is done by line search. Namely, first the margin ...

This paper presents our response to the first international challenge on Facial Emotion Recognition and Analysis. We propose to combine different types of features to automatically detect Action Units in facial images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern histograms and a histogram intersection k...

The relationship between the nuclear parameters and model performance is complex, which is from relevance vector machine (RVM) regression model based on Gaussian radial basis kernel function. Aiming at the problem of how to determine the kernel parameters of RVM, a method to selecting kernel parameter of RVM based on AIC criterion is proposed. Firstly, a novel of statistic Q is proposed based o...

In this paper we propose a novel approach for modeling kernels in Radial Basis Function networks. The method provides an extra degree of flexibility to the kernel structure. This flexibility comes through the use of modifier functions applied to the distance computation procedure, essential for all kernel evaluations. Initially the classifier uses an unsupervised method to construct the network...

This paper studies the asymptotic approximation power of radial basis function neural networks in the sup norm. The methods used are constructive and based on discretization of approximate identities. The effect of the kernel on the approximation order is discussed.

Die stetig steigende Anzahl von Bildern erfordert Verfahren zur maschinellen Annotation. Um automatisch semantische Informationen aus den Bildern zu extrahieren, repräsentieren wir die Bilder durch numerische Vektoren, sogenannte BoWHistogramme und klassifizieren diese auf vorgegebene Klassen. Als Klassifikatoren werden Nearest-Centroid (NC) und Support Vector Machine (SVM) eingesetzt. Auf der ...

The recently proposed “generalized min-max” (GMM) kernel [9] can be efficiently linearized, with direct applications in large-scale statistical learning and fast near neighbor search. The linearized GMM kernel was extensively compared in [9] with linearized radial basis function (RBF) kernel. On a large number of classification tasks, the tuning-free GMM kernel performs (surprisingly) well comp...

Text-mining methods have become a key feature for homeland-security technologies, as they can help explore effectively increasing masses of digital documents in the search for relevant information. This research presents a model for document clustering that arranges unstructured documents into content-based homogeneous groups. The overall paradigm is hybrid because it combines pattern-recogniti...

Radial Basis Probabilistic Neural Network (RBPNN) demonstrates broader and much more generalized capabilities which have been successfully applied to different fields. In this paper, the RBPNN is extended by calculating the Euclidean distance of each data point based on a kernel-induced distance instead of the conventional sum-of squares distance. The kernel function is a generalization of the ...