Practical Deep Learning for Coders 2018 • Hacker News Board

Re: Practical Deep Learning for Coders 2018

#31

Post by jph00 » Mon, Jan 29, 2018, 8:00 PM UTC

brianmorton wrote: post #28

What are the benefits of the in-person "Part 2" in SF? Would it be feasible to fly in weekly for the course?

There are certainly folks that fly in weekly. One student flew in from Australia for the duration! But if you're far away you'd probably be better off applying to be an international fellow, which means you watch the lesson live over Youtube Live and can ask questions and interact with me and the class in real time: http://www.fast.ai/2018/01/17/international-spring-2018/

If you're considering the investment of weekly flights, you should probably first ask the students at http://forums.fast.ai whether they would recommend it.

Re: Practical Deep Learning for Coders 2018

#32

Post by ShirsenduK » Mon, Jan 29, 2018, 8:17 PM UTC

jph00 wrote: post #15

ShirsenduK wrote: post #14

Earlier quoted context omitted.

This is so uncool! This is again going to take up my weekends just like their previous course. :D Congrats on the new course! Thank you. :)

> This is so uncool! Why thank you :) Being uncool is our specialty.

Hottest course in AI town!!!

(I was trying to be sarcastic. Thankful for the courses :)).

Re: Practical Deep Learning for Coders 2018

#33

Post by ultrasounder » Mon, Jan 29, 2018, 8:42 PM UTC

jph00 wrote: post #26

neves wrote: post #24

Earlier quoted context omitted.

Do you have good references about how to setup the environment with a Nvidia GPU in a Windows machine?

Yes, I've provided a step by step walk-through here: http://forums.fast.ai/t/howto-installation-on-windows/10439 This includes setup of fastai, pytorch, cuda90, cudnn, opencv, bcolz, and much more!

Hi Jeremy, I just recently "upgraded" from a Macbook air to a Windoze Gaming Laptop with the GTX1050 GPU just for the reason that one day I could hopefully do all the Fast.ai assignments on my laptop. I think this announcement right here will spur me in taking up this course and Finishing it. I have an actual need for automating some of our IQC/OQC( Incoming and outgoing Quality control) of sub-assemblies and parts that we purchase from our vendors and I hope to leverage what I learn from this course. Thanks a Ton for democratizing Deeplearning and ML for a large population. Ananth

Re: Practical Deep Learning for Coders 2018

#34

Post by zawerf » Mon, Jan 29, 2018, 8:47 PM UTC

Did anyone do Andrew Ng's deeplearning.ai and know how it compares?

Re: Practical Deep Learning for Coders 2018

#35

Post by hackernewsacct » Mon, Jan 29, 2018, 9:09 PM UTC

jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Jeremy, thanks for putting this out. I had issues with part 1, v1 with the AWS set up. But I had none of those issues with this course. As a beginner programmer the template provided via Paperspace is just what I needed. I've been waiting for this course to be released for a really long time now, so I am incredibly excited to have successfully set up the environment and am now FINALLY ready to learn. Thank you!

Re: Practical Deep Learning for Coders 2018

#36

Post by 1024core » Mon, Jan 29, 2018, 9:41 PM UTC

Is this course free? What's the catch? I can't seem to find pricing anywhere.

(this is a genuine question, and not a meta-comment)

Re: Practical Deep Learning for Coders 2018

#37

Post by aphextron » Mon, Jan 29, 2018, 9:49 PM UTC

Can anyone reccomend an "AI for Dummies"? Every resource I've yet to find starts with assuming I have any idea what "Eigenvector" or "Gradient descent" means.

Re: Practical Deep Learning for Coders 2018

#38

Post by jph00 » Mon, Jan 29, 2018, 9:49 PM UTC

ultrasounder wrote: post #33

jph00 wrote: post #26

Earlier quoted context omitted.

Yes, I've provided a step by step walk-through here: http://forums.fast.ai/t/howto-installation-on-windows/10439 This includes setup of fastai, pytorch, cuda90, cudnn, opencv, bcolz, and much more!

Hi Jeremy, I just recently "upgraded" from a Macbook air to a Windoze Gaming Laptop with the GTX1050 GPU just for the reason that one day I could hopefully do all the Fast.ai assignments on my laptop. I think this announcement right here will spur me in taking up this course and Finishing it. I have an actual need for automating some of our IQC/OQC( Incoming and outgoing Quality control) of sub-assemblies and parts t…

My pleasure! You may need to reduce the batch size in a few lessons to fit on that card, FYI.

Re: Practical Deep Learning for Coders 2018

#39

Post by jph00 » Mon, Jan 29, 2018, 9:50 PM UTC

1024core wrote: post #36

Is this course free? What's the catch? I can't seem to find pricing anywhere. (this is a genuine question, and not a meta-comment)

It's free. We're a self-funded non-profit. We do this because we actually want to help people!

Re: Practical Deep Learning for Coders 2018

#40

Post by dkobran » Mon, Jan 29, 2018, 9:52 PM UTC

neves wrote: post #24

jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Do you have good references about how to setup the environment with a Nvidia GPU in a Windows machine?

Dan from Paperspace here. Our fast.ai template is Linux based but you can spinup a GPU backed Windows instance on our cloud if you’re interested in a remote option. Our streaming tech is GPU accelerated so it feels snappy.