Mathematics for Machine Learning by Deisenroth / Faisal & Ong

Most machine learning courses assume a mathematical background their students do not have, and most mathematics texts are written for mathematicians. Mathematics for Machine Learning exists precisely in that gap: it builds the required mathematics from foundations, then shows the four central ML methods those foundations make possible.

What the book covers

• Part I — foundations: linear algebra, analytic geometry, matrix decompositions, vector calculus, probability and distributions, and continuous optimisation
• Part II — the methods: linear regression, principal component analysis, Gaussian mixture models, and support vector machines
• Worked derivations rather than stated results, so you can follow how each method is obtained
• Exercises throughout, with the connective tissue between chapters made explicit

Who it’s for

Students entering a machine learning programme, working engineers who want to read research papers without skipping the equations, and self-learners who have used ML libraries and now want to understand what they call.

Edition details

• Authors: Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
• Publisher: Cambridge University Press
• Format: Paperback
• ISBN: 9781108455145
• Language: English

Ships free within the United States from Shelfcove.