NIPS 2014 papers
cs.stanford.edu
NIPS 2014 papers
1–10 of 15 posts
Re: NIPS 2014 papers
#293 occurrences of "deep"
Re: NIPS 2014 papers
#3Karpathy constantly shows the gap between "Anyone could've done that" and "Yeah, but he _did_."
Re: NIPS 2014 papers
#4Also check out the octopus visualization. http://cs.stanford.edu/people/karpathy/scholaroctopus/
Re: NIPS 2014 papers
#5I took a stab at trying to interpret the topics output by this run of LDA. Green is one the clearest: generally convolutional deep nets, image classification, empirical work.
Brown seems to have picked up on linear algebra. "Vector", "matrix", "tensor" and "decomposition" all get consistently labeled brown, as do "eigenvalues", "orthogonal" and "sparse".
The rest are not as useful. Black almost always has "number", "set", "tree" and "random", but little else. Purple at times seems to signify topic modeling, but also contains "neural" and "feedforward". Blue seems to be the stats topic, containing "Bayes", "regression", "gaussian", and markov processes. But it also contains random words like "university" and "international".
Overall, very interesting. I wonder if these topics would be even better defined with a higher setting of k.
Re: NIPS 2014 papers
#6A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input is very cool.
The Karpathy paper, too.
I love the cross-modal work that's going on at the moment.
Re: NIPS 2014 papers
#7Karpathy constantly shows the gap between "Anyone could've done that" and "Yeah, but he _did_."
It's only in the last 12 months that it became clear this was possible. The Ng "Zero Shot Learning" paper came out at NIPS2013, and given the lead time for a paper like that I think they must have started work at about that time.
Re: NIPS 2014 papers
#8I took a stab at trying to interpret the topics output by this run of LDA. Green is one the clearest: generally convolutional deep nets, image classification, empirical work. Brown seems to have picked up on linear algebra. "Vector", "matrix", "tensor" and "decomposition" all get consistently labeled brown, as do "eigenvalues", "orthogonal" and "sparse". The rest are not as useful. Black almost always has "number", "…
Yup, it seems k was fixed since the first time these scripts were made for NIPS 2012 (?). Some of the more well-established advances since LDA would also likely help, like HDP.
Re: NIPS 2014 papers
#9Karpathy constantly shows the gap between "Anyone could've done that" and "Yeah, but he _did_."
It's only in the last 12 months that it became clear this was possible. The Ng "Zero Shot Learning" paper came out at NIPS2013, and given the lead time for a paper like that I think they must have started work at about that time.
Wow, those downvotes are pretty strong! Clearly I'm wrong - what am I missing?
Re: NIPS 2014 papers
#10Earlier quoted context omitted.
It's only in the last 12 months that it became clear this was possible. The Ng "Zero Shot Learning" paper came out at NIPS2013, and given the lead time for a paper like that I think they must have started work at about that time.
Wow, those downvotes are pretty strong! Clearly I'm wrong - what am I missing?
This is done using Latent Dirichlet Allocation (LDA). The original algorithm was published by David Blei et al over ten years ago, link to the paper: http://machinelearning.wustl.edu/mlpapers/paper_files/BleiNJ...
There are many machine learning libraries that have good implementations of LDA (e.g. Gensim), so it should be "relatively" straightforward to create the topics and clustering based on the abstracts of the papers.