I 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.<p>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".<p>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".<p>Overall, very interesting. I wonder if these topics would be even better defined with a higher setting of k.
When the papers mention that code will be released, is that right now, or when the conference happens? I couldn't find any links to the code in any of the papers, including the karpathy one
Also check out the octopus visualization. <a href="http://cs.stanford.edu/people/karpathy/scholaroctopus/" rel="nofollow">http://cs.stanford.edu/people/karpathy/scholaroctopus/</a>
<i>A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input</i> is very cool.<p>The Karpathy paper, too.<p>I love the cross-modal work that's going on at the moment.