Here are my notes on the Elements of Statistical Learning 2nd Edition (ESLII) by Hastie et al. This is a wonderful book, full of many insights in statistical learning, and I hope to add in some of my own insights, clarifications, and questions on the different parts of the book.
I am not aiming to replace the book. This is just to compliment reading of the book. I want to give insights, proofs and reimplementations of the different chapters in the book, starting with chapter 2. (Chapter 1 is an easy to understand overview of machine learning.) I am for an intuitive explanation of the math, asking the question; how did they even think of doing this? Tather than just understanding the steps in the proof. I hope that this will help when coming up with one’s own methods.
I assume basic knowledge in statistics, calculus and linear algebra. There are good mathematical resources for these online, and I will post them.
To get a good intuitive foundation of Linear algebra, I highly recommend 3blue1brown’s Essence of Linear Algebra series whenever an operation in a proof seems unintuitive. Though I will try to explain the proofs myself, 3blue1brown’s geometric interpretations of Lin Alg is what inspires my own though process.
I hope that you will enjoy, and if there is anything that you disagree with, want to give your own insights to, or if there are things that you believe are important that I didn’t address, please let me know! There are may subtleties in the wording that contain many insights, and I’m sure that there are ones that I didn’t catch.