We are assisting at a growing interest in the development of learning architectures with application to digital communication systems. Herein, we consider detection/decoding problem. aim developing an optimal neural architecture for such task. The definition criterion is fundamental step. propose use mutual information (MI) channel input-output signal pair, which yields minimization a-posterior...

Most of the existing neural machine translation (NMT) models focus on the conversion of sequential data and do not directly take syntax into consideration. We propose a novel end-to-end syntactic NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our model has an attention mechanism that enables the decoder to generate a translated word while softly alignin...

The forthcoming MPEG-4 standard specifies in its systems part an audiovisual scene description and functionality for the elementary stream management. The elementary streammanagement functionality is introduced here. It consists of a media object description framework that describes the streaming resources that form part of an MPEG-4 presentation and of a synchronization syntax incorporated in ...