There is a early recording of Andrew Ng Stanford course before he became the star of the field.
It is mostly math behind ML.
There are also his lecture notes from 2014 I suppose.
It is really all one need to know. Machine learning or Deep learning is just pattern recognition which uses NNs as the basis for representation foe the "matcher".
The real problem of ML is to find someone who would pay you for this because we are in a bubble.
It is math and algorithms that matters and there are just a few of them. All the tooling could be mastered in a month.
Statistics applied to not fully observable stable systems in the modern day alchemy.
Simulations have similar flaws - once the model does not match reality perfectly one would get an arbitrary wrong results.
Look at all the COVID related simulations and statistical models - all of them are not even close to reality.