內容簡介
在引入開源Deeplearning4j(DL4J)庫用於開發産品級工作流之前,作者Josh Patterson和Adam Gibson介紹瞭深度學習——調優、並行化、嚮量化及建立管道——任何庫所需的基礎知識。通過真實的案例,你將學會在Spark和Hadoop上用DL4J訓練深度網絡架構並運行深度學習工作流的方法和策略。
* 深入機器學習一般概念,特彆是深度學習相關概念
* 理解深度網絡如何從神經網絡基礎演化
* 探索主流深度網絡架構,包括Convolutional和Recurrent
* 學習如何將特定的深度網絡映射到具體的問題
* 一般神經網絡和特定深度網絡架構調優基礎概覽
* 為不同的數據類型使用DL4J的工作流工具DateVec實現嚮量化
* 學習如何在Spark和Hadoop本地使用DL4J
作者簡介
Josh Patterson目前是Skymind的現場工程副總裁。他此前曾在Cloudera擔任高級解決方案架構師,在Tennessee Valley Authority擔任機器學習和分布式係統工程師。
Adam Gibson是Skymind的CTO。Adam曾與財富500強企業、對衝基金、公關公司和創投加速器等機構閤作,創建它們的機器學習項目。他在幫助這些公司處理和闡釋大規模實時數據方麵頗具深厚經驗。
精彩書評
(這本書包含瞭)開發者所需知道的關於真實世界中深度學習如何起步的一切。
—— Grant Ingersoll (Lucidworks的CTO)
目錄
Preface
1. A Review of Machine Learning
The Learning Machines
How Can Machines Learn?
Biological Inspiration
What Is Deep Learning?
Going Down the Rabbit Hole
Framing the Questions
The Math Behind Machine Learning: Linear Algebra
Scalars
Vectors
Matrices
Tensors
Hyperplanes
Relevant Mathematical Operations
Converting Data Into Vectors
Solving Systems of Equations
The Math Behind Machine Learning: Statistics
Probability
Conditional Probabilities
Posterior Probability
Distributions
Samples Versus Population
Resampling Methods
Selection Bias
Likelihood
How Does Machine Learning Work?
Regression
Classification
Clustering
Underfitting and Overfitting
Optimization
Convex Optimization
Gradient Descent
Stochastic Gradient Descent
Quasi-Newton Optimization Methods
Generative Versus Discriminative Models
Logistic Regression
The Logistic Function
Understanding Logistic Regression Output
Evaluating Models
The Confusion Matrix
Building an Understanding of Machine Learning
2. Foundations of Neural Networks and Deep Learning.
Neural Networks
The Biological Neuron
The Perceptron
Multilayer Feed-Forward Networks
Training Neural Networks
Backpropagation Learning
Activation Functions
Linear
Sigmoid
Tanh
Hard Tanh
Softmax
Rectified Linear
Loss Functions
Loss Function Notation
Loss Functions for Regression
Loss Functions for Classification
Loss Functions for Reconstruction
Hyperparameters
Learning Rate
Regularization
Momentum
Sparsity
3. Fundamentals of Deep Networks
4. Major Architectures of Deep Networks
5. Building Deep Networks
6. Tuning Deep Networks
7. Tuning Specific Deep Networks Architecture
8. Vectorization
9. Using Deep Learning and DL4J on Spark
A. What Is Artificial Intelligence?
B. RL4J and Reinforcement Learning
C. Numbers Everyone Should Know
D. Neural Networks and Backpropagation: A Mathematical Approach
E. Using the ND4J API
深度學習(影印版) [Deep Learning] 下載 mobi epub pdf txt 電子書 格式