Chapter 1, The Apache Spark Ecosystem, provides a comprehensive overview of the Apache Spark modules and its different deployment modes.
Chapter 2, Deep Learning Basics, introduces the basic concepts of deep learning.
Chapter 3, Extract, Transform, Load, introduces the DL4J framework and presents training data ETL examples from diverse sources.
Chapter 4, Streaming, presents data streaming examples using Spark and DL4J DataVec.
Chapter 5, Convolutional Neural Networks, goes deeper into the theory behind CNNs and model implementation through DL4J.
Chapter 6, Recurrent Neural Networks, goes deeper into the theory behind RNNs and model implementation through DL4J.
Chapter 7, Training Neural Networks in Spark, explains how to train CNNs and RNNs with DL4J and Spark.
Chapter 8, Monitoring and Debugging Neural Network Training, goes through the facilities provided by DL4J to monitor and tune a neural network at training time.
Chapter 9, Interpreting Neural Network Output, presents some techniques to evaluate the accuracy of a model.
Chapter 10, Deploying on a Distributed System, talks about some of the things you need to take into consideration when configuring a Spark cluster, and the possibility of importing and running pre-trained Python models in DL4J.
Chapter 11, NLP Basics, introduces the core concepts of natural language processing (NLP).
Chapter 12, Textual Analysis and Deep Learning, covers some examples of NLP implementations through DL4J, Keras, and TensorFlow.
Chapter 13, Convolution, talks about convolution and object recognition strategies.
Chapter 14, Image Classification, drives through the implementation of an end-to-end image classification web application.
Chapter 15, What's Next for Deep Learning?, tries to give an overview of what's in store in the future for deep learning.