Building Machine Learning Projects with TensorFlow(用tensorflow做机器学习项目)
Chapter 1, Exploring and Transforming Data, guides the reader in undersanding the main
components of a TensorFlow application, and the main data-exploring methods included.
Chapter 2, Clustering, tells you about the possibility of grouping different kinds of data
elements, defining a previous similarity criteria.
Chapter 3, Linear Regression, allows the reader to define the first mathematical model to
explain diverse phenomena.
Chapter 4, Logistic Regression, is the first step in modeling non-linear phenomena with a very
powerful and simple mathematical function.
Chapter 5, Simple Feedforward Neural Networks, allows you to comprehend the main
component, and mechanisms of neural networks.
Chapter 6, Convolutional Neural Networks, explains the functioning and practical application,
of this recently rediscovered set of special networks.
Chapter 7, Recurrent Neural Networks, shows a detailed explanation of this very useful
architecture for temporal series of data.
Chapter 8, Deep Neural Networks, offers an overview of the latest developments on mixed
layer type neural networks.
Chapter 9, Running Models at Scale – GPU and Serving, explains the ways of tackling
problems of greater complexity, by dividing the work into coordinating units.
Chapter 10, Library Installation and Additional Tips, covers the installation of TensorFlow on
Linux, Windows, and Mac architectures, and presents you with some useful code tricks that
will ease day-to-day tasks
tensorflow for deep learning.pdf
1. Introduction to Deep Learning. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Machine Learning eats Computer Science 10
Deep Learning Primitives 11
Fully Connected Layer 11
Convolutional Layer 12
Recurrent Neural Network (RNN) Layers 13
Long Short-Term Memory (LSTM) Cells 14
Deep Learning Zoo 14
LeNet 14
AlexNet 15
ResNet 16
Neural Captioning Model 16
Google Neural Machine Translation 17
One shot models 18
AlphaGo 19
Generative Adversarial Networks 20
Neural Turing Machines 21
Deep Learning Frameworks 22
Empirical Learning 25
2. Introduction toTensorfow Primitives. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
Introducing Tensors 27
Scalars, Vectors, and Matrices 28
Matrix Mathematics 31
Tensors 33
Tensors in physics. 35
Mathematical Asides 37
Basic Computations in Tensorflow 38
Initializing Constant Tensors. 38
Sampling Random Tensors 40
Tensor Addition and Scaling 40
Matrix Operations 41
Tensor types 42
Tensor Shape Manipulations 43
Introduction to Broadcasting 44
Imperative and Declarative Programming 45
Tensorflow Graphs 46
Tensorflow Sessions 46
Tensorflow Variables 47
Review 4
Introduction to TensorFlow(tensorflow 入门)
改书分为install tensorflow、tensorflow 概念(graph、tensor、session等)、hello Word(简单示例)、回归代码实现、分类代码实现;在整体上了解tensorflow的运行原理与应用,是入门的好材料。
word2vec.zip
该代码包为Google code,现在Google上找不到该代码包,所以上传到此供大家下载。(安装指南:在Linux上进入该目录中运行make编译word2vec工具:(如果其中makefile文件后有.txt后缀,将其去掉)在当前目录下执行make进行编译,生成可执行文件(编译过程中报出很出Warning,暂且不管))
人工智能及其应用 第4版(蔡自兴).pdf
人工智能及其应用 第4版(蔡自兴)主要介绍了知识表示法、非经典推理、计算智能、专家系统、机器学习等内容是目前最新的人工智能经典书籍,有兴趣的可以学习一下。
concurrency programming in java (java并发编程)
该文档为英文版的java并发编程书,其中介绍了锁、状态依赖、原子循环等重要内容,有兴趣的可以下下来学习一下。
java8使用规格说明书.pdf
该文档属于英文高清版的JAVA8使用规格说明书,里面有完整的书签,可以对其中的文本进行编辑。
Programming Pig(pig编程).pdf
pig编程实战详细介绍了实现mr的功能原理,是pig初学者的理想资料。pdf
Programming Hive (hive编程).pdf
hive编程这本书全面介绍了hive的各个特性以及如何使用hive来存取数据,是hive初学者理想的自学资料。
Learning spark (学习spark)
该文档为2015年出版的英文高清版,其中的内容可进行复制,并附有书签,方便读者阅读,不失为spark入门学习的指引者。
数据库系统概论(第四版)].王珊等.扫描版.pdf
该书是由王珊和萨师煊编著的第四版《数据库系统概论》,其以sqlserver为基础,内容写的很是深刻易懂。