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

Sparse autoencoders

In general, standard autoencoders produce dense internal representations. This means that most of the values are different from zero. In some cases, however, it's more useful to have sparse code that can better represent the atoms belonging to a dictionary. In this case, if , , we can consider each sample as the overlap of specific atoms weighted accordingly. To achieve this objective, we can simply apply an L₁ penalty to the code layer, as explained in Chapter 2, Loss functions and Regularization. The loss function for a single sample, therefore, becomes the following:

In this case, we need to consider the extra hyperparameter α, which must be tuned to increase the sparsity without a negative impact on the accuracy. As a general rule of thumb, I suggest starting with a value equal to 0.01 and then reducing it until the desired result has been achieved. In most cases, higher values yield very poor performance, and therefore they are generally avoided...