Re:Deep Reinforcement Learning in Depth in 60 Days
by andri27 on Sunday September 02, 2018 @11:37AM
(#17897340)
My goal is to put together, for each week, theoretical material done by experienced people (e.g. video,papers,books ecc..) with projects done by myself.
Re:Deep Reinforcement Learning in Depth in 60 Days
by DrNuke on Sunday September 02, 2018 @12:04PM
(#17897439)
> There has been a rise lately in Machine Learning/Deep Learning resources which have zero original projects or original ideas
Nah, not lazy imho. On one side, the barrier to just messing around is pretty low these days but the barrier to original projects or ideas is quite steep without a strong domain expertise and a nicely assembled dataset; on the other side, the arXiv repository and the most relevant conferences are possibly more suited to originality than the average list by Noob McNobody from his/her basement in Nowhere, Planet Earth?
Re:Deep Reinforcement Learning in Depth in 60 Days
by curiousgal on Sunday September 02, 2018 @11:32AM
(#17897318)
> While that's an educational option, it's, in my opinion, lazy and avoids furthering the ecosystem as a whole.
I've missed HN's cynical take on things lately. There's absolutely nothing wrong with using those ressources to learn. You say it's an educational "option" whereas the entire purpose is educational.
Re:Deep Reinforcement Learning in Depth in 60 Days
by minimaxir on Sunday September 02, 2018 @11:38AM
(#17897343)
True, there's nothing wrong with using these resources, although I'm a bit disappointed when a "Awesome List of ML/DL" pops up every other week on HN with similar content/topics.
I apologize for being overly cynical.
Re:Deep Reinforcement Learning in Depth in 60 Days
by curiousgal on Sunday September 02, 2018 @11:45AM
(#17897370)
I am equally disappointed as well but I realized that my disappointment should be directed towards the people upvoting such lists and not towards whomever's creating them, because, on a personal level, such lists are useful. For the entire field however, I agree with you.
There has been a rise lately in Machine Learning/Deep Learning resources which have zero original projects or original ideas, just a list of papers/blog posts (or worse, MOOC teachers/YouTubers who do that and obfuscate the source of the original ideas). While that's an educational option, it's, in my opinion, lazy and avoids furthering the ecosystem as a whole.