Here we list some materials studied in ADSL. All these lectures/books will be helpful to people who study machine learning.
- Linear algebra – Linear algebra is necessary for studying machine learning. We recommend the online open lecture ‘Linear dynamical Systems’ by professor Stephen Boyd at Stanford. This lecture deals with applied linear algebra, so if you need to study basic linear algebra first, take the open course ‘Linear algebra’ by Gilbert Strang at MIT.
Linear dynamical Systems by Boyd – https://see.stanford.edu/Course/EE263
Linear algebra by Strang – https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra-spring-2010/
- Introduction to Statistical Learning (ISLR) – This lecture is for basic Statistics and machine learning. All students in ADSL read through this book and solve all the problems in the book. This book is also good for learning basic R. The full version of the book and the lecture of two authors are both online.
- Deeplearning book – This book is like a textbook for people who study deep learning. All students in ADSL read through this book as well. The full version of this book is also free.
Deeplearning book – https://www.deeplearningbook.org/
- Pattern Recognition and Machine Learning (PRML) – With this book, you can study PRML with sophisticated formulas. It is quite difficult to study all the contents in this book alone, so we recommend you to read this book together. The full version of the book is also available online.
- Analytics – If you want to develop an intuition for mathematics, we recommend you study Analytics. If you are a student at Seoul National University, you can take a lecture on Analytics1 by Prof. Kye.