In this paper we argue that the choice of the SVM cost parameter can be critical. We then derive an algorithm that can fit the entire path of SVM solutions for every value of the cost parameter, with essentially the same computational cost as fitting one SVM model.

Image indexing based on Modified Color Co-occurrence Matrix (MCCM) is proposed in this paper. First, CCM is simplified to represent the number of color (hue) pairs between adjacent pixels in the image. And then, CCM is split into diagonal and non-diagonal elements that constitute two elements of MCCM. Indexing the image by MCCM could exploit shape information in abstract level. Proposed MCCM is...

The inversion of matrix is widely used in many scientific applications and engineering calculations and this operation requires a large number of computational efforts and storage space. In order to reduce the consumed time and to increase efficiency, a parallel algorithm for matrix inversion based on classic Gauss-Jordan elimination with pivoting is proposed. Upon the multi-core DSPs platform,...

We introduce an approach to learning convolution filters whose joint output can be fed to a classifier that labels them as belonging to linear structures or not. The filters are learned using sparse synthesis techniques but we show that enforcing constraints is not required at run-time to achieve good classification performance. In practice, this is important as it drastically reduces the compu...

Abstract: We address the problem of deriving Pareto optimal solutions of multiple objective optimization problems with predetermined upper bounds on trade-offs. As shown, this can be achieved by a linear transformation of objective functions. Each non-diagonal element of the transformation matrix is related to a bound on the trade-off between a pair of the objective functions.

State-of-the-art 3D morphable model (3DMM) is used widely for 3D face reconstruction based on a single image. However, this method has a high computational cost, and hence, a simplified 3D morphable model (S3DMM) was proposed as an alternative. Unlike the original 3DMM, S3DMM uses only a sparse 3D facial shape, and therefore, it incurs a lower computational cost. However, this method is vulnera...

We show how to employ leave-K-out cross-validation in Unsupervised Kernel Regression, a recent method for learning of nonlinear manifolds. We thereby generalize an already present regularization method, yielding more flexibility without additional computational cost. We demonstrate our method on both toy and real data.

The aim of this paper is to present a new method to compare modulo histograms. In these histograms, the type of elements are cyclic, for instance, the hue in colour images. The main advantage is that there is an important timecomplexity reduction respect the methods presented before. The distance between histograms that we present is defined on a structure called signature, which is a lossless ...

Pseudospectra of matrix polynomials have been systematically investigated in the last years, since they provide important insights into the sensitivity of polynomial eigenvalue problems. An accurate approximation of the pseudospectrum of a matrix polynomial P (λ) by means of the standard grid method is computationally high demanding. In this paper, we propose an improvement of the grid method, ...

Reliable and eecient techniques are now available to synthesize gain-scheduled controllers. Such techniques take advantage of Linear Matrix Inequality (LMI) characterizations of gain-scheduled controllers and provide a global and systematic treatment of the gain-scheduling problem. This paper examines how such controller structures, designed in continuous time, can be discretized and implemente...