Deep Learning for Natural Language Processing

Chapter 5

Recurrent Neural Networks

Learning Objectives

By the end of this chapter, you will be able to:

• Describe classical feedforward networks
• Differentiate between feedforward neural networks and recurrent neural networks
• Evaluate the application of backpropagation through time for recurrent neural networks
• Describe the drawbacks of recurrent neural networks
• Use recurrent neural networks with keras to solve the author attribution problem

This chapter aims to introduce you to recurrent neural networks and their applications, as well as their drawbacks.

Introduction

We encounter different kinds of data in our day-to-day lives, and some of this data has temporal dependencies (dependencies over time) while some does not. For example, ...