Enforcing orthogonality in convolutional neural networks is a remedy for gradient
vanishing/exploding problems and sensitivity to perturbation. Many previous approaches for …

Nowadays the topic of sampling in a shift-invariant space is having a significant impact: it
avoids most of the problems associated with classical Shannon's theory. Under appropriate …

The aim of this article is to derive a sampling theory in U-invariant subspaces of a separable
Hilbert space ℋ where U denotes a unitary operator defined on ℋ. To this end, we use some …

In this paper, we study the invertibility of M-variate Laurent polynomial N times P matrices.
Such matrices represent multidimensional systems in various settings such as filter banks …

If a function of time is limited to the band from 0 to W cycles per second, it is completely
determined by giving its ordinates at a series of discrete points spaced 1/2W seconds apart …

Neural networks are general-purpose function approximators. Given a problem, engineers
or scientists select a hypothesis space of functions with specific properties by designing the …

We study the invertibility of M-variate polynomial (respectively: Laurent polynomial) matrices
of size N by P. Such matrices represent multidimensional systems in various settings …

We study the invertibility of M-variate polynomial (respectively: Laurent polynomial) matrices
of size N by P. Such matrices represent multidimensional systems in various settings …