Live data from Hacker News

Deep Learning: Not Just for Silicon Valley

fast.ai

1–10 of 23 posts

Re: Deep Learning: Not Just for Silicon Valley

#2
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...

Re: Deep Learning: Not Just for Silicon Valley

#4
post #2

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,…

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.

Re: Deep Learning: Not Just for Silicon Valley

#5
post #2

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,…

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

Re: Deep Learning: Not Just for Silicon Valley

#8
post #2

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,…

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

Re: Deep Learning: Not Just for Silicon Valley

#9
post #8
post #2

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,…

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 .

Re: Deep Learning: Not Just for Silicon Valley

#10
post #2

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,…

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