@jeremy Can you say more about testing each line of code? e.g. Pitfalls and examples or themes of tests
Whatās wrong with the real-time chat here on the forums, @Even? Is there something that youāre finding is missing? Happy to invest in Slack if thereās a clear need.
I find the forums to be much less real time and also much more broken up. A forum is a great place to pose and answer questions and I think itās an excellent part of the community, but itās not well suited to quick freeform back and forths or answering of questions in real time.
I jumped on board the MLPeeps slack created by @brendan and had an awesome multiday conversation with @xinxin.li.seattle thatās been a great experience. It could possibly have taken place on the forums, but I feel like with the delays and the extra spacing it would have taken a lot longer to convey the information.
I just want to make sure I understand the issue and confirm that we really need a separate tool, rather than reconfigure this one - so I hope you donāt mind if I ask a few follow up questions?..
Have you tried using private chat groups on the forum here? They are real-time. And we could create a forum on even just a thread for random chat, which also would provide a real-time conversation venue.
Having used Slack a lot and Discourse a reasonable amount Iāve personally found Discourse (i.e. these forums) a superset of Slackās functionality. Iāve seen conversations between the Discourse devs and various folks on twitter where theyāve tried to resolve similar questions, but it never seems to get far. Iām not sure why, but it seems like no-one has quite managed to clearly articulate either why Discourse is, or isnāt, an adequate real-time chat platform.
What are the delays and spacing that you are referring to?
I want to create the most vibrant possible DL community. If we have it all in one place, but that place doesnāt provide what people need, then it wonāt be as good as it can be. But if itās split over multiple places, then by definition each place will have a weaker community and less momentum, and will also mean more places for people to follow.
Would love to hear any thoughts other folks have about this too. @brendan maybe you have some comments too? @xinxin.li.seattle?
We donāt have any funds to pay anyone, but weāre very interested in collaborating with all students to help with (and get help for) their and our projects!
3 Likes
Iām certainly considering it. Perhaps this could be build into the podcast schedule weāre planning - for instance sometimes it could be an interview with someone who has just published an interesting paper, and I could spend time in the podcast working through it myself (just like I have been in class, but with the addition of an interview too). Would that be of interest?
7 Likes
I think PhD requirements wonāt be as strict as they seem (except perhaps at large companies, where thereās less flexibility). They just donāt want to waste their time with people who donāt know their stuff, and until now that often meant having a PhD.
Also, @rachel wrote on this topic just a few days ago, and I think thereās much good advice here: http://www.fast.ai/2017/04/06/alternatives/
1 Like
Personally I find it easiest to run a different experiment on each GPU. Having said that, Pytorch makes it trivially easy to run multi-GPU training (see the DCGAN lesson for an example).
We certainly would like to, although we donāt have any specific plans or schedules for this. Iām hoping that students will start building on the tools weāve created themselves as well. Iām already seeing some of the tools discussing and used on the Kaggle forums.
If you or anyone is interested in developing on top of any of the code or ideas from the course, weād love to help any way we can.
Iām not sure that there are any yet. @timanglade has been working on this - maybe he has some suggestions?
Not really, Iām afraid. Itās one of the most challenging issues in ML. I always try to come up with a strong baseline, by creating a very simple but reasonably effective initial model. Often that means using nearest neighbors, and/or a random forest.
I agree. I hope to develop some good techniques in the coming months. If Iām successful, Iāll certainly want to teach them! 
3 Likes
That would be amazing. I think the podcast alone is probably a great start and covers a lot of what Iām looking for. I love podcasts and will definitely be subscribing as soon as itās available.
Something that might be worth rolling into the podcast as well is @samwitās suggestion of an overview of new papers and findings in deep learning in every episode. Not only would that round out the episode with additional content, but Iām guessing itāll drive a lot of interest in the podcast itself.
I know a lot of podcasts that are recorded live as video as well, with a chat audience, so the two could be one and the same.
1 Like
Right - thatās pretty much what I was thinking.
I havenāt heard one with a chat audience before - could you suggest a couple I could listen to?
2 Likes
The examples I have are a little off topic; I tried to find one in the data science or ML area but there doesnāt seem to be any. The only examples I know of are from gaming, which used to be a hobby of mine before I became addicted to deep learning ;-).
But I would imagine it would work almost exactly as the class does, with a youtube live announcement, a thread on the forum for people to discuss, and then the audio gets put on itunes and the videos can go on your youtube channel.
I did not intend for a paid internship. I actually meant to ask if I can collaborate with any project you are working on. Staying in India , I never had an opportunity to learn from persons like you . I have dedicated my 6 months to 1 year of full time to learn applied deep learning. Thanks for this initiative .
Yes, of course we can collaborate! Perhaps on lung cancer diagnosis?
Sure . I am in. Let me know how can we start.