Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. First, apologies for the brevity of this review-I had written a version with more detailed comments and had found a few typos, but can't find it now. This paper is an application of DNNs to a novel area (finding mathematical identities) and my feeling is that while the ideas are novel, this seems like preliminary work that maybe doesn't quite rise to the level of a NIPS publication. Specifically, your method doesn't seem to show particularly impressive performance in discovering identities, even though you only gave it a very limited set of inputs. The expressions that you were finding identities on were from such a limited set that it would probably have been easier to just work out some mathematical rule to discover them rather than applying DNNs; it seems like using a sledgehammer to crack a nut.