3D卷积说话人识别：用于说话人验证的深度学习和3D卷积神经网络

Whitepaper-Acceleratoring Throughput in Permissioned Blockchain Networks

YouTube推荐系统Paper[2016]-Deep Neural Networks for YouTube Recommendations.pdf YouTube推荐系统Paper[2016]-Deep Neural Networks for YouTube Recommendations.pdf

AI NEUROSCIENCE: VISUALIZING AND UNDERSTANDING DEEP NEURAL NETWORKS

Texture Synthesis Using Convolutional Neural Networks

O'Reilly -802.11- Wireless Networks the definitive guide 802.11无线网络权威指南，纯PDF格式，非照片

计算机网络 第五版（英文电子版）Computer Networks, 5th Edition

This book attempts to simplify and present the concepts of deep learning in a very comprehensive manner, with suitable, full-fledged examples of neural network architectures, such as Recurrent Neural Networks (RNNs) and Sequence to Sequence (seq2seq), for Natural Language Processing (NLP) tasks. The book tries to bridge the gap between the theoretical and the applicable. It proceeds from the theoretical to the practical in a progressive manner, first by presenting the fundamentals, followed by the underlying mathematics, and, finally, the implementation of relevant examples. The first three chapters cover the basics of NLP, starting with the most frequently used Python libraries, word vector representation, and then advanced algorithms like neural networks for textual data. The last two chapters focus entirely on implementation, dealing with sophisticated architectures like RNN, Long Short-Term Memory (LSTM) Networks, Seq2seq, etc., using the widely used Python tools TensorFlow and Keras. We have tried our best to follow a progressive approach, combining all the knowledge gathered to move on to building a questionand- answer system. The book offers a good starting point for people who want to get started in deep learning, with a focus on NLP. All the code presented in the book is available on GitHub, in the form of IPython notebooks and scripts, which allows readers to try out these examples and extend them in interesting, personal ways.

Opportunistic unlicensed access to the (tem- porarily) unused frequency bands across the licensed radio spectrum is currently being inves- tigated as a means to increase the efficiency of spectrum usage. Such opportunistic access calls for implementation of safeguards so that ongo- ing licensed operations are not compromised. Among different candidates, sensing-based access, where the unlicensed users transmit if they sense the licensed band to be free, is partic- ularly appealing due to its low deployment cost and its compatibility with the legacy licensed sys- tems. The ability to reliably and autonomously identify unused frequency bands is envisaged as one of the main functionalities of cognitive radios. In this article we provide an overview of the regulatory requirements and major chal- lenges associated with the practical implementa- tion of spectrum sensing functionality in cognitive radio systems. Furthermore, we outline different design trade-offs that have to be made in order to enhance various aspects of the sys- tem’s performance.