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.

'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.’

Source: De Leesclub van Alles