The Deep Learning with Keras Workshop

9. Sequential Modeling with Recurrent Neural Networks

Overview

This chapter will introduce you to sequential modeling—creating models to predict the next value or series of values in a sequence. By the end of this chapter, you will be able to build sequential models, explain Recurrent Neural Networks (RNNs), describe the vanishing gradient problem, and implement Long Short-Term Memory (LSTM) architectures. You will apply RNNs with LSTM architectures to predict the value of the future stock price value of Alphabet and Amazon.

Introduction

In the previous chapter, we learned about pre-trained networks and how to utilize them for our own applications via transfer learning. We experimented with VGG16 and ResNet50, two pre-trained networks ...