In supervised machine learning, some algorithms are restricted to discrete data and thus need to discretize continuous attributes. In this paper, we present a new discretization method called MODL, based on a Bayesian approach. The MODL method relies on a model space of discretizations and on a prior distribution defined on this model space. This allows the setting up of an evaluation criterion...

‎Linear semi-infinite programming problem is an important class of optimization problems which deals with infinite constraints‎. ‎In this paper‎, ‎to solve this problem‎, ‎we combine a discretization method and a neural network method‎. ‎By a simple discretization of the infinite constraints,we convert the linear semi-infinite programming problem into linear programming problem‎. ‎Then‎, ‎we use...

A new numerical method is presented for the heat equation with discontinuous coefficients based on a Crank–Nicolson scheme and a conforming finite element space discretization. In the proposed method each node of the spatial discretization may have the global timestep split into an arbitrary number of local substeps in order to pursue a local improvement of the time discretization in the region...

This paper proposes an experimental evaluation of various discretization schemes in three different evolutionary systems for inductive concept learning. The various discretization methods are used in order to obtain a number of discretization intervals, which represent the basis for the methods adopted by the systems for dealing with numerical values. Basically, for each rule and attribute, one...

We analyze a numerical algorithm for solving radiative transport equation with vacuum or reflection boundary condition that was proposed in [4] with angular discretization by finite element method and spatial discretization by discontinuous Galerkin or finite difference method.

We consider a fully discrete approximation of the H gradient flow of an energy integral where the energy density is given by the sum of a nonnegative multi-well potential term and a bending energy term. The spatial discretization is based on a Fourier spectral method, which is combined with an implicit Euler time discretization. The numerical method is shown to be stable and to exhibit optimal ...