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?

1. https://developer.nvidia.com/deep-learning-software

2. http://deeplearning.net/software/theano/index.html

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.

if you are comfortable with Docker, check out https://github.com/t0mk/ultimate-mldev

I'm in Part 2 of the course now, and it's shaping up to be really really good as well.

How high have you gotten on dogs VS cats? Just curious, am submitting there as well.:)

I was #150 but moved down a bit, one guy I'm doing the course with got into the 90s (but I think moved down a bit too)

Do you have to spend money on AWS for this course?

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.

If you want you can just watch the videos. You won't learn quite as deeply but he goes over his solution to the homework.

Yes you do. But you can turn off your machine after you are done with your calculations. You probably end up with not more than $20 a month.

That's a good guess! I spent nearly exactly $20 until week 4, including a whole Sunday of fiddling around with the Cats & Dogs dataset