In this paper we address the problem of decoding 2D convolutional codes over the erasure channel. In particular, we present a procedure to recover bursts of erasures that are distributed in a diagonal line. To this end we introduce the notion of balls around a burst of erasures which can be considered an analogue of the notion of sliding window in the context of 1D convolutional codes. The main...

An important class of codes widely used in applications is the class of convolutional codes. Most of the literature of convolutional codes is devoted to convolutional codes over finite fields. The extension of the concept of convolutional codes from finite fields to finite rings have attracted much attention in recent years due to fact that they are the most appropriate codes for phase modulati...

This chapter describes the main architectures proposed in the literature to implement the channel decoders required by the WiMax standard, namely convolutional codes, turbo codes (both block and convolutional) and LDPC. Then it shows a complete design of a convolutional turbo code encoder/decoder system for WiMax.

Convolutional and bidirectional recurrent neural networks have achieved considerable performance gains as acoustic models in automatic speech recognition in recent years. Latest architectures unify long short-term memory, gated recurrent unit and convolutional neural networks by stacking these different neural network types on each other, and providing short and long-term features to different ...

| New nested convolutional codes and rate-compatible punctured convolutional (RCPC) codes with high constraint lengths and wide range of code rates are presented. It is shown that these codes are almost as good as the existing optimum convolutional codes for the same rates. The eeects of varying the design parameters of the RCPC codes, i.e. the mother code rate, the puncturing period and the co...

Maximum distance profile (MDP) convolutional codes have the property that their column distances are as large as possible. It has been shown that, transmitting over an erasure channel, these codes have optimal recovery rate for windows of a certain length. Reverse MDP convolutional codes have the additional advantage that they are suitable for forward and backward decoding algorithms. Beyond th...

Recently, deep Convolutional Neural Networks have been shown to outperform Deep Neural Networks for acoustic modelling, producing state-of-the-art accuracy in speech recognition tasks. Convolutional models provide increased model robustness through the usage of pooling invariance and weight sharing across spectrum and time. However, training convolutional models is a very computationally expens...

Convolutional autoencoders (CAEs) are unsupervised feature extractors for high-resolution images. In the preprocessing step, whitening transformation has widely been adopted to remove redundancy by making adjacent pixels less correlated. Pooling is a biologically inspired operation to reduce the resolution of feature maps and achieve spatial invariance in convolutional neural networks. Conventi...

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard “dense” implementations of convolutional networks are very ineffici...