A convolutional code C can be naturally viewed as a submodule of the free module F[z]. In this way we can view a convolutional code as dual to a linear, shift invariant and complete behavior. The known representations of linear behaviors carry over by duality to representations for convolutional codes. In the behavioral literature one can find two natural generalized first order forms and we re...

Convolutional network techniques have recently achieved great success in vision based detection tasks. This paper introduces the recent development of our research on transplanting the fully convolutional network technique to the detection tasks on 3D range scan data. Specifically, the scenario is set as the vehicle detection task from the range data of Velodyne 64E lidar. We proposes to presen...

This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding, for example for recognition on mobile platforms or in embedded systems. In this paper we propose C...

Scene labeling is a challenging computer vision task. It requires the use of both local discriminative features and global context information. We adopt a deep recurrent convolutional neural network (RCNN) for this task, which is originally proposed for object recognition. Different from traditional convolutional neural networks (CNN), this model has intra-layer recurrent connections in the con...

Low density parity check (LDPC) block codes have been shown to achieve near capacity performance for binary transmission over noisy channels. Block codes, however, require splitting the data to be transmitted into frames, which can be a disadvantage in some applications. Convolutional codes, on the other hand, have no such requirement, and are hence well suited for continuous transmission. In [...

In this paper, we propose a novel unsupervised deep learning model, called PCA-based Convolutional Network (PCN). The architecture of PCN is composed of several feature extraction stages and a nonlinear output stage. Particularly, each feature extraction stage includes two layers: a convolutional layer and a feature pooling layer. In the convolutional layer, the filter banks are simply learned ...

It is well accepted that convolutional neural networks play an important role in learning excellent features for image classification and recognition. However, in tradition they only allow adjacent layers connected, limiting integration of multi-scale information. To further improve their performance, we present a concatenating framework of shortcut convolutional neural networks. This framework...

LDPC convolutional codes, also known as spatially coupled LDPC codes, have attracted considerable attention due to their promising properties. By coupling the protographs from different positions into a chain and terminating the chain properly, the resulting convolutional-like LDPC code ensemble is able to produce capacityachieving performance in the limit of large parameters. In addition, opti...

We give a general method to construct MDS one-dimensional convolutional codes. Our method generalizes previous constructions [5]. Moreover we give a classification of one-dimensional Convolutional Goppa Codes and propose a characterization of MDS codes of this type. Introduction One of the main problems in coding theory is the construction of codes with a large distance, such as so-called MDS c...

Convolutional Turbo encoding is employed for channel coding in most modern communication standards. It has been shown to provide better bit error rate performance than convolutional encoding but this increase in performance comes at a considerable cost in implementation complexity to achieve required decoding throughput. Convolutional Turbo codes (CTC) are constructed by a parallel concatenatio...