Book Image

Deep Learning with Hadoop

By : Dipayan Dev
Book Image

Deep Learning with Hadoop

By: Dipayan Dev

Overview of this book

This book will teach you how to deploy large-scale dataset in deep neural networks with Hadoop for optimal performance. Starting with understanding what deep learning is, and what the various models associated with deep neural networks are, this book will then show you how to set up the Hadoop environment for deep learning. In this book, you will also learn how to overcome the challenges that you face while implementing distributed deep learning with large-scale unstructured datasets. The book will also show you how you can implement and parallelize the widely used deep learning models such as Deep Belief Networks, Convolutional Neural Networks, Recurrent Neural Networks, Restricted Boltzmann machines and autoencoder using the popular deep learning library Deeplearning4j. Get in-depth mathematical explanations and visual representations to help you understand the design and implementations of Recurrent Neural network and Denoising Autoencoders with Deeplearning4j. To give you a more practical perspective, the book will also teach you the implementation of large-scale video processing, image processing and natural language processing on Hadoop. By the end of this book, you will know how to deploy various deep neural networks in distributed systems using Hadoop.
Table of Contents (16 chapters)
Deep Learning with Hadoop
About the Author
About the Reviewers
Customer Feedback

Bi-directional RNNs

This section of the chapter will discuss the major limitations of RNNs and how bi-directional RNN, a special type of RNN helps to overcome those shortfalls. Bi-directional neural networks, apart from taking inputs from the past, takes the information from the future context for its required prediction.

Shortfalls of RNNs

The computation power of standard or unidirectional RNNs has constraints, as the current state cannot reach its future input information. In many cases, the future input information coming up later becomes extremely useful for sequence prediction. For example, in speech recognition, due to linguistic dependencies, the appropriate interpretation of the voice as a phoneme might depend on the next few spoken words. The same situation might also arise in handwriting recognition.

In some modified versions of RNN, this feature is partially attained by inserting some delay of a certain amount (N) of time steps in the output. This delay helps to capture the future...