Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech. However, studies have suggested to favor a certain type of convolutional operations when building a d...

Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. Although DNNs have been ...

WiMAX based on IEEE Std. 802.16 carries high data rates and large coverage to wireless networks. It provide high speed wireless broadband connectivity building the gap between 3G and Wireless LAN (WLAN).The main focus of this paper is on 802.16d OFDM PHY layer. The simulation will compare the performance of SF and STF – OFDM over different SUI channel models. Forward error correction is used to...

This paper presents cltorch, a hardware-agnostic backend for the Torch neural network framework. cltorch enables training of deep neural networks on GPUs from diverse hardware vendors, including AMD, NVIDIA, and Intel. cltorch contains sufficient implementation to run models such as AlexNet, VGG, Overfeat, and GoogleNet. It is written using the OpenCL language, a portable compute language, gove...

For rate R = 1=2 convolutional codes with 16 states there exists a gap between Heller’s upper bound on the free distance and its optimal value. This correspondence reports on the construction of 16state, binary, rate R = 2=4 nonlinear trellis and convolutional codes having dfree = 8; a free distance that meets the Heller upper bound. The nonlinear trellis code is constructed from a 16-state, ra...

We present flattened convolutional neural networks that are designed for fast feedforward execution. The redundancy of the parameters, especially weights of the convolutional filters in convolutional neural networks has been extensively studied and different heuristics have been proposed to construct a low rank basis of the filters after training. In this work, we train flattened networks that ...

This seminar paper focusses on convolutional neural networks and a visualization technique allowing further insights into their internal operation. After giving a brief introduction to neural networks and the multilayer perceptron, we review both supervised and unsupervised training of neural networks in detail. In addition, we discuss several approaches to regularization. The second section in...

Convolutional neural networks are known to be effective in learning complex image classification tasks. However, how to design the architecture or complexity of the network structure requires a more quantitative analysis of the architecture design. In this paper, we study the effect of model complexity on generalization capability of the convolutional neural networks on large-scale, real-life d...

This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural network approach on RGB videos and extend it to three dimensional convolutions. Thi...

We study a serially interleaved concatenated code construction, where the outer code is a standard convolutional code, and the inner code is a recursive convolutional code of rate 1. Focus is put on the ubiquitous inner differential encoder (used in particular to resolve phase ambiguities), double differential encoder (used to resolve both phase and frequency ambiguities), and another rate 1 re...