Teaching is a great way to learn (for me). I wish I was better at it though. Hence these subsequent videos, lectures, notes and resources are my attempts at improving
my teaching abilities! These range from topics that I am studying to topics that are just for "fun". If I really want to master something I should be able to explain it in depth.
A course I developed to focus on major machine learning algorithms and building them from scratch.
Too much content is focused on calling packages and models without understanding fundamentals. This course changes that.
Astrophysical Fluid Dynamics
A course derived from Prof. Chung-Pei Ma in Berkeley
when I first took the class. I hope to cover a bit more than what was originally planed with some exploration on
numerical solvers and also General Relativistic Magneto Hydrodynamics. (also some notes were Howard Huang when I couldnt read my own hand writing)
This will be a lab like course where I explain key algorithmic machine learning techniques and then manually implement them myself
live (or go line-by-line atleast). My rule is I am NOT allowed to call any major computational package unless
I have handwrote some version of it myself already. Note: this is a lab course and thus can only be best experienced
through engaging with the interactive component of writing key concepts with me. This is usually a few lines of code
each lecture which describe the heart of the algorithm.