Mathematics for Machine Learning

Marc Peter Deisenroth; A. Aldo Faisal; Cheng Soon Ong

doi:10.1017/9781108679930

Frontmatter

pp i-iv

Contents

pp v-viii

List of Symbols

pp ix-x

Preface

pp xi-xiv

DOI: https://doi.org/10.1017/9781108679930.001

Acknowledgments

pp xv-xviii

DOI: https://doi.org/10.1017/9781108679930.002

Part I - Mathematical Foundations

pp 1-2

1 - Introduction and Motivation

pp 3-7

DOI: https://doi.org/10.1017/9781108679930.003

2 - Linear Algebra

pp 8-56

DOI: https://doi.org/10.1017/9781108679930.004

3 - Analytic Geometry

pp 57-81

DOI: https://doi.org/10.1017/9781108679930.005

4 - Matrix Decompositions

pp 82-119

DOI: https://doi.org/10.1017/9781108679930.006

5 - Vector Calculus

pp 120-151

DOI: https://doi.org/10.1017/9781108679930.007

6 - Probability and Distributions

pp 152-200

DOI: https://doi.org/10.1017/9781108679930.008

7 - Continuous Optimization

pp 201-222

DOI: https://doi.org/10.1017/9781108679930.009

Part II - Central Machine Learning Problems

pp 223-224

8 - When Models Meet Data

pp 225-259

DOI: https://doi.org/10.1017/9781108679930.010

9 - Linear Regression

pp 260-285

DOI: https://doi.org/10.1017/9781108679930.011

10 - Dimensionality Reduction with Principal Component Analysis

pp 286-313

DOI: https://doi.org/10.1017/9781108679930.012

11 - Density Estimation with Gaussian Mixture Models

pp 314-334

DOI: https://doi.org/10.1017/9781108679930.013

12 - Classification with Support Vector Machines

pp 335-356

DOI: https://doi.org/10.1017/9781108679930.014

References

pp 357-366

Index

pp 367-372

DOI: https://doi.org/10.1017/9781108679930.015

‘This book provides great coverage of all the basic mathematical concepts for machine learning. I'm looking forward to sharing it with students, colleagues, and anyone interested in building a solid understanding of the fundamentals.'

Joelle Pineau - McGill University, Montreal

‘The field of machine learning has grown dramatically in recent years, with an increasingly impressive spectrum of successful applications. This comprehensive text covers the key mathematical concepts that underpin modern machine learning, with a focus on linear algebra, calculus, and probability theory. It will prove valuable both as a tutorial for newcomers to the field, and as a reference text for machine learning researchers and engineers.'

Christopher Bishop - Microsoft Research Cambridge

'This book provides a beautiful exposition of the mathematics underpinning modern machine learning. Highly recommended for anyone wanting a one-stop-shop to acquire a deep understanding of machine learning foundations.'

Pieter Abbeel - University of California, Berkeley

Author

Marc Peter Deisenroth, University College London
Marc Peter Deisenroth is DeepMind Chair in Artificial Intelligence at the Department of Computer Science, University College London. Prior to this, he was a faculty member in the Department of Computing, Imperial College London. His research areas include data-efficient learning, probabilistic modeling, and autonomous decision making. Deisenroth was Program Chair of the European Workshop on Reinforcement Learning (EWRL) 2012 and Workshops Chair of Robotics Science and Systems (RSS) 2013. His research received Best Paper Awards at the International Conference on Robotics and Automation (ICRA) 2014 and the International Conference on Control, Automation and Systems (ICCAS) 2016. In 2018, he was awarded the President's Award for Outstanding Early Career Researcher at Imperial College London. He is a recipient of a Google Faculty Research Award and a Microsoft P.hD. grant.
A. Aldo Faisal, Imperial College London
A. Aldo Faisal leads the Brain and Behaviour Lab at Imperial College London, where he is faculty at the Departments of Bioengineering and Computing and a Fellow of the Data Science Institute. He is the director of the 20Mio£ UKRI Center for Doctoral Training in AI for Healthcare. Faisal studied Computer Science and Physics at the Universität Bielefeld (Germany). He obtained a Ph.D. in Computational Neuroscience at the University of Cambridge and became Junior Research Fellow in the Computational and Biological Learning Lab. His research is at the interface of neuroscience and machine learning to understand and reverse engineer brains and behavior.
Cheng Soon Ong, Data61, CSIRO
Cheng Soon Ong is Principal Research Scientist at the Machine Learning Research Group, Data61, Commonwealth Scientific and Industrial Research Organisation, Canberra (CSIRO). He is also Adjunct Associate Professor at Australian National University. His research focuses on enabling scientific discovery by extending statistical machine learning methods. Ong received his Ph.D. in Computer Science at Australian National University in 2005. He was a postdoc at Max Planck Institute of Biological Cybernetics and Friedrich Miescher Laboratory. From 2008 to 2011, he was a lecturer in the Department of Computer Science at Eidgenössische Technische Hochschule (ETH) Zürich, and in 2012 and 2013 he worked in the Diagnostic Genomics Team at NICTA in Melbourne.

No metrics are currently available for this content

How to use additional resources?

These resources are supplementary materials for instructors and/or students that support enhanced teaching and learning outcomes. Such resources provide additional content, or present content in an alternative form to support instructors working on course material. Some of these resources are available to instructors only, and not all titles will have supplementary materials.

View resources

Format: Hardback

Dimensions: 253 x 177 mm

Page extent: 398 pages

Weight: 0.95 kg

Availability: Manufactured on demand: supplied direct from the printer

Contains: 3 b/w illus. 106 colour illus.

Format: Paperback

Dimensions: 253 x 177 mm

Page extent: 398 pages

Weight: 0.8 kg

Availability: In stock

Contains: 3 b/w illus. 106 colour illus.

Mathematics for Machine Learning

Author

How to use additional resources?

Share

Subjects