• ## Notes on Information Theory (master page)

This is the master page for Notes on Machine Learning posts, in which I summarize in a succinct and straighforward fashion what I learn from Information Theory course by Mathematical Monk, along with my own thoughts and related resources. Notes on Machine Learning 1: Information theory and Coding To be...

• ## Notes on Machine Learning 3: Decision theory

(ML 3.1) Decision theory (Basic Framework) Idea. “Minimize expected loss” Example. Spam (classification): $x, y, \hat{y}$ Loss function $L(y, \hat{y}) \in \mathbb{R}$ Loss can be thought of as reward or utility depending on the sign of the value. General framework: State $s$ (unknown) Observation (known) e.g, $x$ Actoin $a$ Loss...

• ## Notes on Deep Reinforcement Learning

In this page I summarize in a succinct and straighforward fashion what I learn from Deep Reinforcement Learning course by Sergey Levine, along with my own thoughts and related resources. I will update this page frequently, like every week, until it’s complete. Acronyms RL: Reinforcement Learning DRL Deep Reinfocement Learning...