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

Pooling layers

In a deep convolutional network, pooling layers are extremely useful elements. There are two main kinds of these structures: max pooling and average pooling. They both work on patches , shifting horizontally and vertically according to the predefined stride value and transforming the patches into single pixels according to the following rules:

There are two main reasons that justify the use of these layers. The first one is dimensionality reduction with limited information loss (for example, if we set the strides to (2, 2), it's possible to halve the dimensions of an image/feature map). Clearly, pooling techniques can be more or less lossy (max pooling in particular), and the specific result depends on the single image.

In general, pooling layers try to summarize the information contained in a small chunk into a single pixel. This idea is supported by a perceptual-oriented approach; in fact, when the pools are not very large, it's rather...