Re:A blog I started on Neural Networks and Probability
by abhirag on Thursday November 30, 2017 @03:10PM
(#15819064)
This might be of interest to you :) -- Probability Through Problems[http://www.springer.com/in/book/9780387950631]
It's like the difference between supervised learning and RL. In one you just get a dataset, in the other you get a playground - a dynamic dataset where you can explore and test hypothesis.
Selecting the problems requires real flair, it's one thing to understand the subject, and quite another to understand the usual pitfalls and stumbling blocks of students learning it.