Books and other resources

Machine Learning

• "Elements of Statistical Learning" by Hastie, Tibshirani and Friedman. Second Edition. (pdf available)
• "Learning Theory from First Principles" by Francis Bach (pdf available)
• "Machine Learning: A Probabilistic Approach" by K. Murphy (NOTE -- Second Edition recently appeared)

Deep Learning

• Dive into Deep Learning by Aston Zhang, Zack Lipton, Mu Li, Alex Smola supported by a community of other contributors
• Deep learning book by Ian Goodfellow, Yoshua Bengio and Aaron Courville
• deeplearning.net hub (some pages slightly outdated)

• Calculus tutorials from Harvey Mudd College, especially Multivariable Calculus and Linear Algebra
• The MIT OpenCourseWare on Mathematics
• Calculus.org a huge list of problems and exams with solutions.
• Waterloo resources ?

• All of Statistics
• Papoulis (more advanced, suited for EECS graduate programs)
• Teukolski teaches statistics along with probability. An excellent introductory book that should be more hyped.
• Chapters and appendices in the above ML/Statistical learning books

Additional research articles that will be discussed in class will be posted on the Lecture notes page, as will my own course notes.

Books in related fields you should have if you are serious about Machine Learning

• For graph theory West - "Introduction to gra.h theory"
• For algorithms and data structures, I recommend the classic CRLS, aka Cormen, Leiserson & Rivest "Introduction to Algorithms".
• On optimization there is "Convex optimization" by Boyd and Vandenberghe available on the web)
• and the ever useful "Numerical recipes" by Press, Teukolsky, Vetterling and Flannery (NR) which is available on the web (text and code!) (Note: the freely available edition is an older one).
• For more advanced optimization there is Nocedal and Wright
• Finally, don't miss another classic -- Elements of Information Theory by Cover and Thomas.