4.38 avg rating — 45 ratings

"A more recent addition to Strang's canon. This will get you up to speed quickly either as introduction or refresher on Linear Algebra and its applications to basic ML and statistical algorithms."

4.26 avg rating — 403 ratings

"More of a reference than a textbook, this will fill in a lot of the gaps that are left out of Casella and Berger's book."

4.17 avg rating — 396 ratings

"Going through this book takes a bit more mathematical maturity, but it should be accessible if you have gotten through, for example, Blitzstein's book on Probability. "

4.51 avg rating — 173 ratings

"Fantastic and thorough introduction to counting problems, probability, and basic statistical theorems (LLN, CLT). Tons of homework problems, many with solutions that can be found online."

4.25 avg rating — 698 ratings

"Strang is known for his linear algebra texts. He also teaches an online LA course on MIT's OCW, which can be a good supplement."

4.52 avg rating — 1,002 ratings

"If you need a calculus refresher, this is the one."

4.32 avg rating — 1,904 ratings

"Machine learning has made a lot of advances since this book was published (there is no deep learning in here), but the basics are all here and you can learn a ton."

4.39 avg rating — 439 ratings

"A very short book that gives an overview of learning theory that is accessible and not overwhelming. This book really isn't just a cookbook, but it's for people who want to go a little deeper into why ML even works at all."

4.43 avg rating — 1,888 ratings

"The "ESL" is one of the classic ML books. If you are up to speed with your probability and linear algebra, this book should be quite accessible."

4.44 avg rating — 2,123 ratings

"The immediate consensus modern classic on Deep Learning. They literally wrote the book."