This paper introduces a general Bayesian framework for obtaining sparse solutions to regression and classification tasks utilising models linear in the parameters. Although this framework is fully general, we illustrate our approach with a particular specialisation that we denote the `relevance

and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ 2 distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels

in the literature including decision tree based algorithms, statistical algorithms and instance based learning methods. We show on ten UCI datasets that the LS-SVM sparse approximation procedure can be successfully applied.

Learning general functional dependencies is one of the main goals in machine learning. Recent progress in kernel-based methods has focused on designing flexible and powerful input representations. This paper addresses the complementary issue of problems involving complex outputs suchas multiple

with sparse feature maps as appear for string kernels, allowing us to train a string kernel SVM on a 10 million real-world splice data set from computational biology. We integrated multiple kernel learning in our machine learning toolbox SHOGUN for which the source code is publicly available at

There are many successful applications to take advantages of massive parallelization on GPU for deep learning algorithm. In this project, I implemented a basic deep learning algorithm, i.e. Autoencoder. Core parts of this project are based on CUBLAS and CUDA kernels. I will first briefly introduce

Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image subwindows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential χ 2 kernels

learning widely applicable to many practical learning problems. We describe an approach to self-taught learning that uses sparse coding to construct higher-level features using the unlabeled data. These features form a succinct input representation and significantly improve classification performance. When

of the design matrix. Experimental results are given and connections to Kernel-PCA, Sparse Kernel Feature Analysis, and Matching Pursuit are pointed out. 1. Introduction Many recent advances in machine learning such as Support Vector Machines [Vapnik, 1995], Regularization Networks [Girosi et al., 1995

in an attempt to minimize leave--one--out error. This gives a convex optimization problem which constructs a sparse linear classifier in feature space using the kernel technique. As such the algorithm possesses many of the same properties as SVMs. The main novelty of the algorithm is that apart from the choice