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.

作者：Professor Kwang-Cheng Chen，Professor Ramjee Prasad 出版：Wiley 2009 目录 Preface xi 1 Wireless Communications 1 1.1 Wireless Communications Systems 1 1.2 Orthogonal Frequency Division Multiplexing (OFDM) 3 1.2.1 OFDM Concepts 4 1.2.2 Mathematical Model of OFDM System 5 1.2.3 OFDM Design Issues 9 1.2.4 OFDMA 21 1.3 MIMO 24 1.3.1 Space-Time Codes 24 1.3.2 Spatial Multiplexing Using Adaptive Multiple Antenna Techniques 27 1.3.3 Open-loop MIMO Solutions 27 1.3.4 Closed-loop MIMO Solutions 29 1.3.5 MIMO Receiver Structure 31 1.4 Multi-user Detection (MUD) 34 1.4.1 Multi-user (CDMA) Receiver 34 1.4.2 Suboptimum DS/CDMA Receivers 37 References 40 2 Software Defined Radio 41 2.1 Software Defined Radio Architecture 41 2.2 Digital Signal Processor and SDR Baseband Architecture 43 2.3 Reconfigurable Wireless Communication Systems 46 2.3.1 Unified Communication Algorithm 46 2.3.2 Reconfigurable OFDM Implementation 47 2.3.3 Reconfigurable OFDM and CDMA 47 2.4 Digital Radio Processing 48 2.4.1 Conventional RF 48 2.4.2 Digital Radio Processing (DRP) Based System Architecture 52 References 58 3 Wireless Networks 59 3.1 Multiple Access Communications and ALOHA 60 3.1.1 ALOHA Systems and Slotted Multiple Access 61 3.1.2 Slotted ALOHA 61 3.1.3 Stabilised Slotted ALOHA 64 3.1.4 Approximate Delay Analysis 65 3.1.5 Unslotted ALOHA 66 3.2 Splitting Algorithms 66 3.2.1 Tree Algorithms 67 3.2.2 FCFS Splitting Algorithm 68 3.2.3 Analysis of FCFS Splitting Algorithm 69 3.3 Carrier Sensing 71 3.3.1 CSMA Slotted ALOHA 71 3.3.2 Slotted CSMA 76 3.3.3 Carrier Sense Multiple Access with Collision Detection (CSMA/CD) 79 3.4 Routing 82 3.4.1 Flooding and Broadcasting 83 3.4.2 Shortest Path Routing 83 3.4.3 Optimal Routing 83 3.4.4 Hot Potato (Reflection) Routing 84 3.4.5 Cut-through Routing 84 3.4.6 Interconnected Network Routing 84 3.4.7 Shortest Path Routing Algorithms 84 3.5 Flow Control 89 3.5.1 Window Flow Control 89 3.5.2 Rate Control Schemes 91 3.5.3 Queuing Analysis of the Leaky Bucket Scheme 9

Neural_Networks_for_Applied_Sciences_and_Engineering，学习神经网络的资料

国外经典的教课书，从国外网站下载的。是通信专业的课的经典教科书。

ImageNet classification with deep convolutional neural networks 中文翻译

About This Book Build your own low-power, wireless network using ready-made Arduino and XBee hardware Create a complex project using the Arduino prototyping platform A guide that explains the concepts and builds upon them with the help of examples to form projects Who This Book Is For This book is targeted at embedded system developers and hobbyists who have some working knowledge of Arduino and who wish to extend their projects using wireless connectivity.

提供了Neural networks and deep learning这本书所有的章节pdf版内容。另外，读者如果想要书中源代码，可以从https://github.com/mnielsen/neural-networks-and-deep-learning下载。

贝叶斯网络的R语言实现，贝叶斯网络的R语言实现，贝叶斯网络的R语言实现，贝叶斯网络的R语言实现，贝叶斯网络的R语言实现。

两年一度的计算机视觉国际顶级会议 International Conference on Computer Vision（ICCV 2017）在意大利威尼斯开幕。Google Brain 研究科学家Ian Goodfellow在会上作为主题为《生成对抗网络(Generative Adversarial Networks)》的Tutorial 最新演讲, 介绍了GAN的原理和最新的应用。