The future we imagine for ourselves in terms of technology is closing in to become a stunning reality- all thanks to the ever growing field and scope of Machine Learning. Being the fastest growing field of Computer Science with far- reaching applications, there is a great demand of developers and researchers in almost every tech company around the world. This book- “Understanding Machine Learning: From Theory to Algorithms”, is one of the best sources to enter the area and to be adept in the same.
About the Book
The aim of the textbook is to introduce Machine Learning, in a way that’d be easy to understand for anyone, with or without a solid mathematical background. It makes us acquainted with algorithmic paradigms, along with the theory in a principled way. It offers a theoretical account of the fundamentals of the concept, including the mathematical derivations which transform these principles into practical working algorithms. The book starts off with a chapter purely based on Foundations, which defines learning, introduces the concept of a learning model, bias, the VC (Vapnik- Chervonenkis) dimension to get the reader to adapt to the new concept.
The book then moves onto the theory and algorithmic part of the models, including various types of learning problems, the various methods to solve them which include Linear Predictors, Stochastic Gradient Descent, Decision Trees, Nearest Neighbours, and Neural Networks etc. It finally transcends into more advanced algorithms of Online Learning- which is one of the most sought- after techniques used in business like e- commerce, dives deeper into efficient feature selections and generations, fundamental theorem of learning theory, and ends with the emerging theoretical concept of PAC-Bayes approach.
The book is specifically designed for undergraduates, or beginning graduates, and the text and style makes the fundamentals and advanced algorithms of machine learning accessible to experts and non- experts in statistics, computer science, mathematics and engineering.
About the Authors
Shai Shalev-Shwartz: is a PhD recipient from the Hebrew University in 2007. He served as a research assistant professor at the Toyota Technological Institute in Chicago and is now a professor at the School of Computer Science and Engineering at The Rachel and Selim Benin School of Computer Science and Engineering, Hebrew University of Jerusalem, Israel. He has also worked at Mobileye on autonomous driving.
Shai Ben-David: was a post- doctoral fellow at the University of Toronto in Mathematics and CS Departments after his PhD from Hebrew University. He has served as a faculty in esteemed institutes like Technion (Israel Institute of Technology), Australian National University, Canberra, Cornell University, and is now at the School of Computer Science, University of Waterloo. His research interests are statistical and computational machine learning, among wide spectrum of topics in Computer Science