|aMachine learning fundamentals : a concise introduction / |cHui Jiang.
260
|aCambridge, United Kingdom ;|aNew York, NY :|bCambridge University Press,|c2021
300
|axviii, 380 p. :|bill. (some col.) ;|c27 cm.
504
|aIncludes bibliographical references and index.
520
|a"This lucid, accessible introduction to supervised machine learning presents core concepts in a focused and logical way that is easy forbeginners 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, boostedtrees, HMMs, and LDAs, plus popular deep learning methods such asconvolution neural nets, attention, transformers, and GANs. Organized in acoherent presentation framework that emphasizes the big picture, the textintroduces each method clearly and concisely "from scratch" based on thefundamentals. All methods and algorithms are described by a clean andconsistent style, with a minimum of unnecessary detail. Numerous casestudies and concrete examples demonstrate how the methods can be applied ina variety of contexts. Hui Jiang is Professor of Electrical Engineering andComputer Science at York University, where he has been since 2002. His mainresearch interests include machine learning, particularly deep learning, andits applications to speech and audio processing, natural languageprocessing, and computer vision. Over the past 30 years, he has worked on awide range of research problems from these areas and published hundreds oftechnical articles and papers in the mainstream journals and top-tierconferences. His works have won the prestigious IEEE Best Paper Award and the ACL Outstanding Paper honor"--|cProvided by publisher.