Introduction to Machine Learning: From Math to Code

Introduction to Machine Learning: From Math to Code

Emphasizing how and why machine learning algorithms work, this introductory textbook bridges the gap between the theoretical foundations of machine learning and its practical algorithmic and code-level implementation. Over 85 thorough worked examples, in both Matlab and Python, demonstrate how algorithms are implemented and applied whilst illustrating the end result. Over 75 end-of-chapter problems empower students to develop their own code to implement these algorithms, equipping them with hands-on experience. Matlab coding examples demonstrate how a mathematical idea is converted from equations to code, and provide a jumping off point for students, supported by in-depth coverage of essential mathematics including multivariable calculus, linear algebra, probability and statistics, numerical methods, and optimization. Accompanied online by instructor lecture slides, downloadable Python code and additional appendices, this is an excellent introduction to machine learning for senior undergraduate and graduate students in Engineering and Computer Science. ‘This book provides clear explanations of fundamental machine learning algorithms alongside practical implementations in both Python and MATLAB. It also offers a brief introduction to modern deep learning techniques, making it an excellent resource for senior undergraduates, graduate students, and aspiring researchers.’ Jiang Li, Old Dominion University Explore how and why machine learning algorithms work with this self-contained, hands-on introduction using Matlab and Python. Ruye Wang is an Emeritus Professor of Engineering at Harvey Mudd College, with over thirty years of experience in teaching courses in Engineering and Computer Science. Previously a Principal Investigator at the Jet Propulsion Laboratory, NASA, his research interests include image processing, computer vision, machine learning and remote sensing. He is the author of the textbook Introduction to Orthogonal Transforms (2012).