I'm finding this list up to 2016 rather useful:https://github.com/terryum/awesome-deep-learning-papers …
-
-
Show this thread
-
-
.
@karpathy's arxiv-sanity is a great project, and I wondered how the top papers over the past year (http://www.arxiv-sanity.com/top?timefilter=year&vfilter=all … ) would be. But many of the most-saved papers are elementary tutorials, which makes me wonder about the collective(!) judgement of users on the siteShow this thread -
What are your favourite 1-3 AI / ML papers over the past 12-24 months? (And feel free to say what excited you about them?)
Show this thread -
(To clarify the arxiv-sanity remark: nothing against the project or users! But it suggests the collective judgements are from people fairly new to the field - natural, given the influx into deep learning. But curious about the recommendations of ppl who've been at this a while!)
Show this thread -
The suggestions so far are great! Please keep them coming! Also love to hear about classic papers that you particularly like!
Show this thread
End of conversation
New conversation -
-
-
These days I find better use of my time reading dated papers that are considered important now, but perhaps not considered important when they were published. If you like RL, the OpenAI project announced today has nice curated list: https://spinningup.openai.com/en/latest/spinningup/keypapers.html …https://twitter.com/jachiam0/status/1060587899861688320 …
-
Thanks! (In general, in areas I know well, I prefer reading old papers, often very old papers. But I haven't really tried to keep track of AI / ML / DL at all, so I'm sorta catching up.)
-
Curious, BTW: what are the best classic papers that you've read?
-
I've been reading recently: Curious Model-Building Control Systems (Schmidhuber 1991) ftp://ftp.idsia.ch/pub/juergen/curioussingapore.pdf Sections 6 and 7 REINFORCE (Williams 1992) http://www-anw.cs.umass.edu/~barto/courses/cs687/williams92simple.pdf … Parts of Evolving Virtual Creatures (Sims 1994) http://www.karlsims.com/papers/siggraph94.pdf …
-
Ah, that's great! Never heard of the first two! I should really systematically look at all of Schmidhuber's stuff...
-
He's probably one of the few who still hosts papers on a ftp site. This one is an early work about recurrent world models with lots of hand drawn art from 1990: http://people.idsia.ch/~juergen/FKI-126-90_(revised)bw_ocr.pdf …
End of conversation
New conversation -
-
-
By far the best recent paper: https://arxiv.org/abs/1604.00289
-
In addition to that, the NYU philosophy dept AI reading group has been reading... 1. "Reinforcement Learning: An Introduction" https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf … Not novel. But a very nice clear laying out of RL.
- End of conversation
New conversation -
-
-
@chipro sotawhat also does a decent job. Maybe you would want to go through the doc to see what are the criteria used.https://github.com/chiphuyen/sotawhat … - End of conversation
New conversation -
-
-
I follow many researchers on Twitter and use their guidance, along with https://openreview.net/ as I like to see the back and forth between reviewers. There's very regularly useful content beyond what is discussed directly in each respective paper.
-
I'll take a look! Can you give me an example of such content?
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.