I'm now in week 4 of the first round of this MOOC (here: http://course.fast.ai/ ) and it's incredibly intuitive, highly recommended. It's less about the mathematics, more about what has been proven to work, and based on these scores I've gotten quite high in the Kaggle competitions the classes go through (Cats & Dogs, State Farm, Titanic)
The Jupyter noteboks are sometimes still quite messy and deserve some cleanup, but it's all open anyway, should submit a PR...
Completely agree. I love the pragmatic nature of the course and the general attitude (anyone can do DL). It's probably the one MOOC I'd recommend to every developer or CS student. It's really mind blowing how good you can perform compared to what was state of the art not too long ago. Not quite finished with #1 either but can't wait for part 2. The pitch/promise for part 2 is that it'll basically take you to the bleeding edge of current (2017) research...that sounds rather exciting.
For the course setup they say to use an AWS instance. I have a machine with a decent Nvidia GPU in it. What software does it use for the deep learning? Do you use the Nvidia suite directly [1]? Or does Theano [2] have everything built in and you just need drivers?
All of the popular deep learning libraries need cuda drivers with cudnn from nvidia which are free . This course uses theano and keras which are open source .
If you've got a decent NVidia GPU, you should be alright.
I understand that Theano can support other (non-NVidia) GPUs using OpenCL, but I haven't tried this. Part 2 of the course requires TensorFlow (which doesn't support OpenCL, AFAIK), so you're better off sticking with NVidia unfortunately.
No. You can build your own machine, use Google Computer Engine (https://cloud.google.com/gpu/), or even just stick with CPU while you get your feet wet.
I started the course with CPU only, and then switched to a GCE instance (which I run sparingly) when I got tired of waiting for my models to train.
"This 7-week course is designed for anyone with at least a year of coding experience, and some memory of high-school math. You will start with step one—learning how to get a GPU server online suitable for deep learning—and go all the way through to creating state of the art, highly practical, models for computer vision, natural language processing, and recommendation systems. There are around 20 hours of lessons, and you should plan to spend around 10 hours a week for 7 weeks to complete the material. The course is based on lessons recorded during the first certificate course at The Data Institute at USF. Part 2 will be taught at the Data Institute from Feb 27, 2017, and will be available online around May 2017."
The Jupyter noteboks are sometimes still quite messy and deserve some cleanup, but it's all open anyway, should submit a PR...