Book Image

Hands-On Deep Learning with Apache Spark

By : Guglielmo Iozzia
Book Image

Hands-On Deep Learning with Apache Spark

By: Guglielmo Iozzia

Overview of this book

Deep learning is a subset of machine learning where datasets with several layers of complexity can be processed. Hands-On Deep Learning with Apache Spark addresses the sheer complexity of technical and analytical parts and the speed at which deep learning solutions can be implemented on Apache Spark. The book starts with the fundamentals of Apache Spark and deep learning. You will set up Spark for deep learning, learn principles of distributed modeling, and understand different types of neural nets. You will then implement deep learning models, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) on Spark. As you progress through the book, you will gain hands-on experience of what it takes to understand the complex datasets you are dealing with. During the course of this book, you will use popular deep learning frameworks, such as TensorFlow, Deeplearning4j, and Keras to train your distributed models. By the end of this book, you'll have gained experience with the implementation of your models on a variety of use cases.
Table of Contents (19 chapters)
Appendix A: Functional Programming in Scala
Appendix B: Image Data Preparation for Spark

Convolution

The previous two chapters have covered real use case implementation of NLP done through RNNs/LSTMs in Apache Spark. In this and the following chapter, we are going to do something similar for CNNs: we are going to explore how they can be used in image recognition and classification. This chapter in particular covers the following topics:

  • A quick recap on what convolution is, from both the mathematical and DL perspectives
  • The challenges and strategies for object recognition in real-world problems
  • How convolution applies to image recognition and a walk-through of hands-on practical implementations of an image recognition use case through DL (CNNs) by adopting the same approach, but using the following two different open source frameworks and programming languages:
    • Keras (with a TensorFlow backend) in Python
    • DL4J (and ND4J) in Scala
...