Abstract- Kernel trick and projection to tangent spaces are two choices for linearizing the data points lying on Riemannian manifolds. These approaches are used to provide the prerequisites for applying standard machine learning methods on Riemannian manifolds. Classical kernels implicitly project data to high dimensional feature space without considering the intrinsic geometry of data points. ...

We give characterizations of radial Fourier multipliers as acting on radial L functions, 1 < p < 2d/(d + 1), in terms of Lebesgue space norms for Fourier localized pieces of the convolution kernel. This is a special case of corresponding results for general Hankel multipliers. Besides L −L bounds we also characterize weak type inequalities and intermediate inequalities involving Lorentz spaces....

A variable radial coordinate transformation of the phase-only filter (POF) that is dependent on the energy's angular distribution of the target spectrum is used to perform shift- and scale-invariant pattern recognition. The POF of a basic size target and the cumulative energy of its angular distribution are calculated. The filter function is then transformed by means of stretching along the rad...

Complexity of Gaussian radial-basis-function networks, with varying widths, is investigated. Upper bounds on rates of decrease of approximation errors with increasing number of hidden units are derived. Bounds are in terms of norms measuring smoothness (Bessel and Sobolev norms) multiplied by explicitly given functions a(r, d) of the number of variables d and degree of smoothness r. Estimates a...

The special and unique advantages of explosive forming, has developed its use in different industries. Considering the important influence of improving the current explosive forming techniques on increasing the efficiency and control over the explosive forming procedure, the effects of air and water as the energy-conveying medium, and also their differences will be illustrated in this paper. He...

The VMPC function is a combination of triple permutation composition and integer addition. It differs from a simple triple permutation composition with one integer addition operation performed on some of the elements of the permutation. The consequence of this addition operation is corruption of cycle structure of the transformed permutation the fundamental source of the function's resistance t...

We present an in-depth examination of the effectiveness of radial basis function kernel (beyond Gaussian) estimators based on orthogonal random feature maps. We show that orthogonal estimators outperform state-of-the-art mechanisms that use iid sampling under weak conditions for tails of the associated Fourier distributions. We prove that for the case of many dimensions, the superiority of the ...