Book description
Although interest in machine learning has reached a high point, lofty expectations often scuttle projects before they get very far. How can machine learning—especially deep neural networks—make a real difference in your organization? This handson guide not only provides the most practical information available on the subject, but also helps you get started building efficient deep learning networks.
Authors Adam Gibson and Josh Patterson provide theory on deep learning before introducing their opensource Deeplearning4j (DL4J) library for developing productionclass workflows. Through realworld examples, you’ll learn methods and strategies for training deep network architectures and running deep learning workflows on Spark and Hadoop with DL4J.
 Dive into machine learning concepts in general, as well as deep learning in particular
 Understand how deep networks evolved from neural network fundamentals
 Explore the major deep network architectures, including Convolutional and Recurrent
 Learn how to map specific deep networks to the right problem
 Walk through the fundamentals of tuning general neural networks and specific deep network architectures
 Use vectorization techniques for different data types with DataVec, DL4J’s workflow tool
 Learn how to use DL4J natively on Spark and Hadoop
Publisher resources
Table of contents
 Preface
 1. A Review of Machine Learning
 2. Foundations of Neural Networks and Deep Learning
 3. Fundamentals of Deep Networks
 4. Major Architectures of Deep Networks

5. Building Deep Networks
 Matching Deep Networks to the Right Problem
 The DL4J Suite of Tools
 Basic Concepts of the DL4J API
 Modeling CSV Data with Multilayer Perceptron Networks
 Modeling Handwritten Images Using CNNs
 Modeling Sequence Data by Using Recurrent Neural Networks
 Using Autoencoders for Anomaly Detection
 Using Variational Autoencoders to Reconstruct MNIST Digits
 Applications of Deep Learning in Natural Language Processing

6. Tuning Deep Networks
 Basic Concepts in Tuning Deep Networks
 Matching Input Data and Network Architectures
 Relating Model Goal and Output Layers
 Working with Layer Count, Parameter Count, and Memory
 Weight Initialization Strategies
 Using Activation Functions
 Applying Loss Functions
 Understanding Learning Rates
 How Sparsity Affects Learning
 Applying Methods of Optimization
 Using Parallelization and GPUs for Faster Training
 Controlling Epochs and MiniBatch Size
 How to Use Regularization
 Working with Class Imbalance
 Dealing with Overfitting
 Using Network Statistics from the Tuning UI
 7. Tuning Specific Deep Network Architectures
 8. Vectorization

9. Using Deep Learning and DL4J on Spark
 Introduction to Using DL4J with Spark and Hadoop
 Configuring and Tuning Spark Execution
 Setting Up a Maven Project Object Model for Spark and DL4J
 Troubleshooting Spark and Hadoop
 DL4J Parallel Execution on Spark
 DL4J API Best Practices for Spark
 Multilayer Perceptron Spark Example
 Generating Shakespeare Text with Spark and Long ShortTerm Memory
 Modeling MNIST with a Convolutional Neural Network on Spark
 A. What Is Artificial Intelligence?

B. RL4J and Reinforcement Learning
 Preliminaries
 Different Settings

QLearning
 From Policy to Neural Networks the following
 Policy Iteration
 Exploration Versus Exploitation
 Bellman Equation
 Initial State Sampling
 QLearning Implementation
 Modeling Q(s,a)
 Experience Replay
 Convolutional Layers and Image Preprocessing
 History Processing
 Double QLearning
 Clipping
 Scaling Rewards
 Prioritized Replay
 Graph, Visualization, and MeanQ
 RL4J
 Conclusion
 C. Numbers Everyone Should Know
 D. Neural Networks and Backpropagation: A Mathematical Approach
 E. Using the ND4J API
 F. Using DataVec
 G. Working with DL4J from Source
 H. Setting Up DL4J Projects
 I. Setting Up GPUs for DL4J Projects

J. Troubleshooting DL4J Installations
 Previous Installation
 Memory Errors When Installing From Source
 Older Versions of Maven
 Maven and PATH Variables
 Bad JDK Versions
 C++ and Other Development Tools
 Windows and Include Paths
 Monitoring GPUs
 Using the JVisualVM
 Working with Clojure
 OS X and Float Support
 ForkJoin Bug in Java 7
 Precautions
 Different Platforms
 Index
 About the Authors
Product information
 Title: Deep Learning
 Author(s):
 Release date: August 2017
 Publisher(s): O'Reilly Media, Inc.
 ISBN: 9781491914250
You might also like
book
Deep Learning
Ever since computers began beating us at chess, they've been getting better at a wide range …
book
Generative Deep Learning
Generative modeling is one of the hottest topics in AI. It’s now possible to teach a …
book
Grokking Deep Learning
Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging …
book
Deep Learning with PyTorch
Every other day we hear about new ways to put deep learning to good use: improved …