Rogers S., Girolami M. A First Course in Machine Learning

CRC Press, 2012. — 307 p.Machine learning is rapidly becoming one of the most important areas general practice, research and development activity within computing science. This is reflected in the scale of the academic research area devoted subject and the active recruitment of machine learning specialists by international banks and financial institutions as well as companies such Microsoft, Google Yahoo and Amazon.
This growth can be partly explained by the increase in the quantity and diversity of measurements we are able to make of the wotld. A particularly fascinating example arises from the wave of new biological measurement technologies that preceded the sequencing of the first genomes. It is now possible to measure the detailed molecular state of an organism in ways that would have been hard to imagine only a short time ago. Such measurements go far beyond our understanding of these organisms and machine learning techniques have been heavily involved in the distillation of useful structures from them.
This book is based on material presented in a machine learning course in the School of Computing Science at the University of Glasgow, UK. The course, presented to final year undergraduates and taught by postgraduates, is made up of 20 hour-long lectures and 10 hour-long laboratory sessions. In such a short teaching period, it is impossible to cover more than a small fraction of the material that now comes under the banner of machine learning. Our intention when teaching this course, therefore, is to present the core mathematical and statistical techniques required to understand some of the most popular machine learning algorithms and then present a few of these algorithms that span the main problem areas within machine learning: classification, clustering and projection. At the end of the course, the students should have the knowledge and confidence to be able to explore machine learning literature to find methods that are more appropriate for them. The same is hopefully true of readers of this book.Linear Modeling: A Least Squares Approach
Linear Modeling: A Maximum Likelihood Approach
The Bayesian Approach to Machine Learning
Bayesian Inference
Classification
Clustering
Principal Components Analysis and Latent Variable Models