You're reading from Mastering Machine Learning Algorithms Expert techniques for implementing popular machine learning algorithms, fine-tuning your models, and understanding how they work

Product type Paperback

Published in Jan 2020

Publisher Packt

ISBN-13 9781838820299

Length 798 pages

Edition 2nd Edition

Languages

Python

Tools

Keras

Concepts

Machine Learning

Authors (2):

Giuseppe Bonaccorso

View More author details

Table of Contents (28) Chapters

Preface

1. Machine Learning Model Fundamentals

2. Loss Functions and Regularization FREE CHAPTER

3. Introduction to Semi-Supervised Learning

4. Advanced Semi-Supervised Classification

5. Graph-Based Semi-Supervised Learning

6. Clustering and Unsupervised Models

7. Advanced Clustering and Unsupervised Models

8. Clustering and Unsupervised Models for Marketing

9. Generalized Linear Models and Regression

10. Introduction to Time-Series Analysis

11. Bayesian Networks and Hidden Markov Models

12. The EM Algorithm

13. Component Analysis and Dimensionality Reduction

14. Hebbian Learning

15. Fundamentals of Ensemble Learning

16. Advanced Boosting Algorithms

17. Modeling Neural Networks

18. Optimizing Neural Networks

19. Deep Convolutional Networks

20. Recurrent Neural Networks

21. Autoencoders

22. Introduction to Generative Adversarial Networks

23. Deep Belief Networks

24. Introduction to Reinforcement Learning

25. Advanced Policy Estimation Algorithms

26. Other Books You May Enjoy

27. Index

Summary

In this chapter, we introduced the concept of RNNs, emphasizing the issues that normally arise when classic models are trained using the BPTT algorithm. In particular, we explained why these networks cannot easily learn long-term dependencies.

For this reason, new models have been proposed, whose performance was immediately outstanding. We discussed the most famous recurrent cell, called Long Short-Term Memory (LSTM), which can be used in layers that can easily learn all the most important dependencies of a sequence, allowing us to minimize the prediction error even in contexts with very high variance (such as stock market quotations). The last topic was a simplified version of the idea implemented in LSTMs, which led to a model called a Gated Recurrent Unit (GRU). This cell is simpler and more computationally efficient, and many benchmarks confirmed that its performance is approximately the same as LSTM.

In the next chapter, we are going to discuss some models called...