To give an idea of how cutting-edge it was at the time, the well-known RMSProp optimizer was unpublished work that Hinton presented in the course, and people had to cite the presentation slides when they used it in papers published later.
Objectively the quality of the production was pretty mediocre, but the assignments were challenging and I learned a lot. Similar to a real course taught by a professor. The final assignment (ray tracing) only asked for render results so I took it as an opportunity to learn rust.
The content was maybe a little outdated, but I think the concepts haven’t changed much and that’s what I was there for.
Course materials were updated for M1 macs, but there was a little friction in figuring things out.
I plan to take the follow up soon.
The instructor is really passionnate about what she's talking about, which really makes the subject more interesting than I thought it would be.
Perry Mehrling’s course on Money and Banking is good too.
On Coursera, I did Andrew Ng’s machine learning course and Dan Boneh’s cryptography course and both were excellent. Time well spent IMHO.
The next thing I want to take is a WinDbg course. Udemy has one that looks pretty good. I should probably also find a modern assembly language course…