Hacker News new | ask | show | jobs
Fast.ai – Deep Learning from the Foundations (fast.ai)
54 points by shekade 2552 days ago
6 comments

Is the future of computing truly this sort of “AI” that can be learned in an afternoon? No wonder self driving cars have been “just 5 years away” for the last 15 years...
Does this contain math above the high-school level?
This is amazing. I've been following fastai for a few years now and it really is geared towards programmers first. I've used what is taught both directly at work as well as inderectly by being able to better advise on what data we collect.

I even brushed to on my linear algebra to better understand what's going in under the hood.

Kind of an aside - what do you need to learn to create "deep dream" style generative programs, and can you learn it from fast.ai?
The keywords you're looking for are generative adversarial networks. Not sure if the syllabus has it.
That technique is used for a lot of AI generated images, but Deep Dream specifically used a trained recognition network "backwards" to adjust the image.

It's like a generative network without the adversarial part.

Ah yes you are correct
Do I need to do the first part to do this course?
> This course is the second part of fast.ai’s 2019 deep learning series; part 1, Practical Deep Learning for Coders, was released in January, and is a required pre-requisite.
no, I have never watched a course before and watched the first lecture of this last night w/ no issue.