Skip to main content Accessibility help
> Mathematics for Machine Learning

Mathematics for Machine Learning

Marc Peter Deisenroth, University College London, A. Aldo Faisal, Imperial College London, Cheng Soon Ong, Data61, CSIRO


The fundamental mathematical tools needed to understand machine learning include linear algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability and statistics. These topics are traditionally taught in disparate courses, making it hard for data science or computer science students, or professionals, to efficiently learn the mathematics. This self-contained textbook bridges the gap between mathematical and machine learning texts, introducing the mathematical concepts with a minimum of prerequisites. It uses these concepts to derive four central machine learning methods: linear…

  • Add bookmark
  • Cite

Key features

  • A one-stop presentation of all the mathematical background needed for machine learning
  • Worked examples make it easier to understand the theory and build both practical experience and intuition
  • Explains central machine learning methods: linear regression, principal component analysis, Gaussian mixture models and support vector machines

About the book

  • DOI
  • Subjects Computational Science,Computer Science,Machine Learning and Pattern Recognition,Mathematics
  • Format: Hardback
    • Publication date: 23 April 2020
    • ISBN: 9781108470049
    • Dimensions (mm): 253 x 177 mm
    • Weight: 0.95g
    • Contains: 3 b/w illus. 106 colour illus.
    • Page extent: 398 pages
    • Availability: Manufactured on demand: supplied direct from the printer
  • Format: Paperback
    • Publication date: 23 April 2020
    • ISBN: 9781108455145
    • Dimensions (mm): 253 x 177 mm
    • Weight: 0.8g
    • Contains: 3 b/w illus. 106 colour illus.
    • Page extent: 398 pages
    • Availability: In stock
  • Format: Digital
    • Publication date: 20 February 2020
    • ISBN: 9781108679930

      Access options

      Check your access to the full version of this content by using one of the options below

      • Institutional login

        Log in with Open Athens, Shibboleth, or your institutional credentials

        Log in
      • Personal login

        If you have previously obtained access using your personal account

        Log in

      If you should have access and can't see this content please contact customer support