You're reading from Python Machine Learning by Example Build intelligent systems using Python, TensorFlow 2, PyTorch, and scikit-learn

Product type Paperback

Published in Oct 2020

Publisher Packt

ISBN-13 9781800209718

Length 526 pages

Edition 3rd Edition

Languages

Python

Tools

PyTorch

Concepts

Machine Learning

Author (1):

Yuxi (Hayden) Liu

View More author details

Table of Contents (17) Chapters

Preface

1. Getting Started with Machine Learning and Python

2. Building a Movie Recommendation Engine with Naïve Bayes FREE CHAPTER

3. Recognizing Faces with Support Vector Machine

4. Predicting Online Ad Click-Through with Tree-Based Algorithms

5. Predicting Online Ad Click-Through with Logistic Regression

6. Scaling Up Prediction to Terabyte Click Logs

7. Predicting Stock Prices with Regression Algorithms

8. Predicting Stock Prices with Artificial Neural Networks

9. Mining the 20 Newsgroups Dataset with Text Analysis Techniques

10. Discovering Underlying Topics in the Newsgroups Dataset with Clustering and Topic Modeling

11. Machine Learning Best Practices

12. Categorizing Images of Clothing with Convolutional Neural Networks

13. Making Predictions with Sequences Using Recurrent Neural Networks

14. Making Decisions in Complex Environments with Reinforcement Learning

15. Other Books You May Enjoy

16. Index

Overcoming long-term dependencies with Long Short-Term Memory

Let's start with the vanishing gradient issue in vanilla RNNs. Where does it come from? Recall that during backpropagation, the gradient decays along with each time step in the RNN (that is, ); early elements in a long input sequence will have little contribution to the computation of the current gradient. This means that vanilla RNNs can only capture the temporal dependencies within a short time window. However, dependencies between time steps that are far away are sometimes critical signals to the prediction. RNN variants, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), are specifically designed to solve problems that require learning long-term dependencies.

We will be focusing on LSTM in this book as it is a lot more popular than GRU. LSTM was introduced a decade earlier and is more mature than GRU. If you are interested in learning more about GRU and its applications...