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

Hebbian Learning

In this chapter, we're going to introduce the concept of Hebbian learning, based on the methods defined by the psychologist Donald Hebb. These theories immediately showed how a very simple biological law is able to describe the behavior of multiple neurons in achieving complex goals and was a pioneering strategy that linked the research activities in the fields of artificial intelligence and computational neuroscience.

In particular, we are going to discuss the following topics:

  • The Hebb rule for a single neuron, which is a simple but biologically plausible behavioral law.
  • Some variants on the Hebb rule, like Oja's and Covariance rules, that have been introduced to overcome a few stability problems.
  • The final result achieved by a Hebbian neuron, which consists of computing the first principal component of the input dataset.
  • Two neural network models (Sanger's network and Rubner-Tavan's network) that can extract a generic...