About the Book
Packed with real-world examples, industry insights and practical activities, this textbook is designed to teach machine learning in a way that is easy to understand and apply. It assumes only a basic knowledge of technology, making it an ideal resource for students and professionals, including those who are new to computer science. All the necessary topics are covered, including supervised and unsupervised learning, neural networks, reinforcement learning, cloud-based services, and the ethical issues still posing problems within the industry. While Python is used as the primary language, many exercises will also have the solutions provided in R for greater versatility. A suite of online resources is available to support teaching across a range of different courses, including example syllabi, a solutions manual, and lecture slides. Datasets and code are also available online for students, giving them everything they need to practice the examples and problems in the book.
Table of Contents:
Part I. Basic Concepts: 1. Teaching computers to write programs; 2. Python; 3. Cloud computing; Part II. Supervised Learning: 4. Regression; 5. Classification-1; 6. Classification-2; Part III. Unsupervised Learning: 7. Clustering; 8. Dimensionality reduction; Part IV. Neural Networks: 9. Neural networks; 10. Deep learning; Part V. Further explorations: 11. Reinforcement learning; 12. Designing and evaluating ML systems; 13. Responsible AI; Appendices.
About the Author :
Dr. Chirag Shah is a Professor of Information Science at the University of Washington (UW) in Seattle, USA. Before UW, he was at Rutgers University. His research focuses on intelligent information access systems that are also fair, transparent, and trustworthy. Dr. Shah teaches in undergraduate, masters, and Ph.D. programs at UW, focusing on data science and machine learning. He has designed MOOCs and taught several tutorials and short courses at international venues. Dr. Shah has written several books, including the bestselling textbook A Hands-On Introduction to Data Science (2020). He has visited and worked with many tech companies, including Amazon, Brainly, Getty Images, Microsoft Research, and Spotify.
Review :
'Written by a great teacher who truly understands the material, the book is conversational and very approachable, while at the same time covering the material comprehensively. I really appreciated the organization, starting from fundamentals that the reader would know already, and then building knowledge structures from there.' Akhilesh Bajaj, The University of Tulsa
'A much-needed book for learning and teaching the essentials of machine learning for practical usage. It has comprehensive and up-to-date coverage on the practical aspects of machine learning. The chapters on cloud computing and responsible AI cover two topics particularly relevant to today's machine learning practices, yet rarely found at such depth and quality in other machine learning books. This book is self-contained and highly accessible to readers of diverse backgrounds. Materials are organized into five easy-to-follow parts while striking a delicate balance between breadth and depth, and between theory and practice. I highly recommend this book to those who need/want to equip themselves with practical hand-on machine learning skills to get their work done.' Haiping Lu, University of Sheffield
'… clearly and concisely introduces traditional and modern machine learning topics. The book is highly accessible for those who are very new to machine learning across diverse computing environments. Ethical issues that we need to pay more attention to are also discussed, and are a great feature.' Minwoo Lee, Department of Computer Science & School of Data Science, The University of North Carolina at Charlotte
'…an accessible textbook for students of machine learning. The presentations of algorithms are clear and supported by examples. The conceptual questions at the end of each chapter allow students to review key concepts, while hands-on problems prepare students to apply what they have learned to real situations. Shah's book is also a valuable tool for practitioners of machine learning.' Tony Diana, Lecturer, University of Maryland Baltimore County (UMBC)
'… an accessible yet far-reaching treatment of practical machine learning. Professor Shah leverages his years of experience creating, teaching, and applying machine learning, in academia as well as industry, to present material that ranges from classical topics to current trends. The pedagogy allows anyone - new or seasoned - to benefit by trying many hands-on problems in different application areas.' Rishabh Mehrotra, Director, Machine Learning at ShareChat
'… an approachable exposition of machine learning with theories and context based on real-life, practical applications. Professor Shah interweaves theoretical concepts, such as dimensionality reduction, gradient descent, and reinforcement learning, with hands-on examples that are easy to understand. This helps students in the classroom as well as other engineering practitioners who are approaching these topics for real-world use cases.' Madhu Kurup, Vice President, Indeed.com
'A Hands-On Introduction to Machine Learning by Chirag Shah is a very good data science textbook, starting from the basics, that covers many subjects not usually covered in introductory data science books, including cloud computing, deep learning, dimensionality reduction, bias and fairness for a responsible AI, and a comprehensive coverage of model evaluation (more about it below). The explanations are clear and many insights are present throughout the book … authoritative and clear, with well-thought-out examples and use cases and a coverage that rivals that of the best, more advanced books. I highly recommend this book. After reading it, you will understand why its author, Prof Chirag, has received many awards.' Paulo Cysne Rios Jr, Data Science Leader
'As a university instructor myself, I immediately appreciated author and University of Washington professor Chirag Shah's pedagogical approach. This is a gainful learning tool. Every chapter has excellent coverage of the typical machine learning (ML) topics coupled with very helpful 'Try It Yourself' sidebars that allow readers to exercise their understanding of the subjects as they progress through the material. Each chapter also includes a 'Conceptual Questions' and 'Hands-on Examples' feature at the end of each section … All in all I consider this book as a fine new entry into the field of machine learning and deep learning. I plan to add this title to the bibliography I give to my beginning data science students as an educational resource they can consume just after taking my intro class. Kudos to author Shah for seeing a need for this type of text!' Daniel D. Gutierrez, InsideBigData
