As it happens, I literally just now posted the curriculum for part 2 of the course - http://www.fast.ai/2017/01/17/curriculum2/ . If you're near SF, you may want to join us. Either way, I'd love to get feedback on the curriculum - anything you'd like to see added? Anything from part 1 that you'd like to know more about?
I am just getting started actually, so I will provide you more feedback as I complete part 1!
For starters, I found the pairing of the lecture, the code, AND the documentation to be particularly useful. The setup in anaconda really enables to you compare/understand inputs and outputs, which at least for me, is very helpful! Big fan of learning through practical application, which the aforementioned combo is well suited for, imo.
Kudos and thank you (and the team) very much for all of the hard work! I am not sure I'll be able to attend part 2 in person but I will be sure to follow along online. If I am ever in SF at the time of a course, I will certainly apply!
"A key teaching goal for us is that you come away from the course feeling much more comfortable reading, understanding, and implementing research papers. We’ll be sharing some simple tricks that make it much easier to quickly scan and get the key insights from a paper."
My interest is musical style transfer. I'd like to replicate these examples from Sony Computer Science Lab-Paris: http://www.flow-machines.com/odetojoy/
They've published papers, but not code (except for DeepBach).
As it happens, I literally just now posted the curriculum for part 2 of the course - http://www.fast.ai/2017/01/17/curriculum2/ . If you're near SF, you may want to join us. Either way, I'd love to get feedback on the curriculum - anything you'd like to see added? Anything from part 1 that you'd like to know more about?