Book Image

Mastering Machine Learning Algorithms. - Second Edition

By : Giuseppe Bonaccorso
Book Image

Mastering Machine Learning Algorithms. - Second Edition

By: Giuseppe Bonaccorso

Overview of this book

Mastering Machine Learning Algorithms, Second Edition helps you harness the real power of machine learning algorithms in order to implement smarter ways of meeting today's overwhelming data needs. This newly updated and revised guide will help you master algorithms used widely in semi-supervised learning, reinforcement learning, supervised learning, and unsupervised learning domains. You will use all the modern libraries from the Python ecosystem – including NumPy and Keras – to extract features from varied complexities of data. Ranging from Bayesian models to the Markov chain Monte Carlo algorithm to Hidden Markov models, this machine learning book teaches you how to extract features from your dataset, perform complex dimensionality reduction, and train supervised and semi-supervised models by making use of Python-based libraries such as scikit-learn. You will also discover practical applications for complex techniques such as maximum likelihood estimation, Hebbian learning, and ensemble learning, and how to use TensorFlow 2.x to train effective deep neural networks. By the end of this book, you will be ready to implement and solve end-to-end machine learning problems and use case scenarios.
Table of Contents (28 chapters)
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...