Our systems are now restored following recent technical disruption, and we’re working hard to catch up on publishing. We apologise for the inconvenience caused. Find out more

Recommended product

Popular links

Popular links


Machine Learning Fundamentals

Machine Learning Fundamentals

Machine Learning Fundamentals

A Concise Introduction
Hui Jiang, York University, Toronto
November 2021
Available
Hardback
9781108837040

    This lucid, accessible introduction to supervised machine learning presents core concepts in a focused and logical way that is easy for beginners to follow. The author assumes basic calculus, linear algebra, probability and statistics but no prior exposure to machine learning. Coverage includes widely used traditional methods such as SVMs, boosted trees, HMMs, and LDAs, plus popular deep learning methods such as convolution neural nets, attention, transformers, and GANs. Organized in a coherent presentation framework that emphasizes the big picture, the text introduces each method clearly and concisely “from scratch” based on the fundamentals. All methods and algorithms are described by a clean and consistent style, with a minimum of unnecessary detail. Numerous case studies and concrete examples demonstrate how the methods can be applied in a variety of contexts.

    • Succinct rather than exhaustive, the focused presentation and coherent overview framework allows readers to understand the core ideas and learn implementations quickly
    • Over 200 color illustrations and more than 50 worked examples, case studies, lab projects in MATLAB and Python, and numerous exercises aid understanding
    • Covers recent important developments in AI and deep learning as well as traditional supervised machine learning methods

    Reviews & endorsements

    'Dr Jiang has done a superb job in covering many methods, both theoretical and practical, across a broad spectrum of machine learning in this timely book. I worked closely with Dr Jiang on Bayesian speech recognition during late 90's and I have personally witnessed his excellent skills in applying machine learning to solving a wide range of practical problems. In this book, Dr Jiang has expanded his scope into a much wider set of logically organized topics in modern machine learning. The organization of the material is highly unique and cogent. A number of hot topics in machine learning, including deep learning and neural networks, are naturally incorporated in the book, which not only provides sufficient technical depth for the readers but also aligns well with popular toolkits for implementing the related machine learning methods.' Li Deng, formerly of Microsoft Corporation and Citadel LLC

    'It is beautifully designed, with many color images that make the complex subject matter manageable … It is a book for students and developers who are committed to specializing in ML or a specific area of ​​it.' Karl van Heijster , De Leesclub van Alles

    See more reviews

    Product details

    November 2021
    Hardback
    9781108837040
    420 pages
    259 × 207 × 27 mm
    1.06kg
    203 colour illus.
    Available

    Table of Contents

    • 1. Introduction
    • 2. Mathematical Foundation
    • 3. Supervised Machine Learning (in a nutshell)
    • 4. Feature Extraction
    • 5. Statistical Learning Theory
    • 6. Linear Models
    • 7. Learning Discriminative Models in General
    • 8. Neural Networks
    • 9. Ensemble Learning
    • 10. Overview of Generative Models
    • 11. Unimodal Models
    • 12. Mixture Models
    • 13. Entangled Models
    • 14. Bayesian Learning
    • 15. Graphical Models.
      Author
    • Hui Jiang , York University, Toronto

      Hui Jiang is Professor of Electrical Engineering and Computer Science at York University, where he has been since 2002. His main research interests include machine learning, particularly deep learning, and its applications to speech and audio processing, natural language processing, and computer vision. Over the past 30 years, he has worked on a wide range of research problems from these areas and published hundreds of technical articles and papers in the mainstream journals and top-tier conferences. His works have won the prestigious IEEE Best Paper Award and the ACL Outstanding Paper honor.