Voice over IP applications require a playout buffer at the receiver side to smooth network delay variations. Unfortunately, existing algorithms for dynamic playout adjustment designed for wireline networks do not operate correctly in wireless ad hoc networks. These algorithms estimate the end-to-end delay on the set of previous received audio packets. Indeed, such a delay estimation based on pa...

The paper examines the question of how learning multiple tasks interacts with neural architectures and the flow of information through those architectures. It approaches the question by using the idealization of an artificial neural network where it is possible to ask more precise questions about the effects of modular versus nonmodular architectures as well as the effects of sequential vs. sim...

When we represent real-world systems as networks, the directions of links often convey valuable information. Finding module structures that respect link directions is one of the most important tasks for analysing directed networks. Although many notions of a directed module have been proposed, no consensus has been reached. This lack of consensus results partly because there might exist distinc...

[1] In this article, a method for drainage network extraction from high-resolution digital elevation models (DEMs; e.g., those derived from airborne laser swath mapping) is presented, which requires just two user-defined parameters and is capable of handling discontinuous valley networks. The accuracy and robustness of the method are illustrated using synthetic valley networks that mimic the co...

We give a criterion in terms of the boundary for the existence of a proper cocompact action of a word-hyperbolic group on a CAT(0) cube complex. We describe applications towards lattices and hyperbolic 3-manifold groups. In particular, by combining the theory of special cube complexes, the surface subgroup result of Kahn-Markovic, and Agol’s criterion, we find that every subgroup separable clos...

Learning curves show how a neural network is improved as the number of t.raiuing examples increases and how it is related to the network complexity. The present paper clarifies asymptotic properties and their relation of t.wo learning curves, one concerning the predictive loss or generalization loss and the other the training loss. The result gives a natural definition of the complexity of a ne...

In the field of neural networks, feature selection has been studied for the last ten years and classical as well as original methods have been employed. This paper reviews the efficiency of four approaches to do a driven forward features selection on neural networks . We assess the efficiency of these methods compare to the simple Pearson criterion in case of a regression problem.