Export Reviews, Discussions, Author Feedback and Meta-Reviews

I have a concern that the quantitative results are misleading and/or wrong. I have a suspicion that the model may be performing similarly to a computer graphics engine ... where it generates very good naturalistic images, but where most real images would be assigned extremely low probability. This could make for a fine paper, but the results would need to be presented in a way that makes this clear. Detailed comments as follow: 45 - 'indicating a better density model...' don't think this part follows 57-61 - Should note these aren't actually generative models as typically defined. Though p(visible hidden) is straightforward, p(hidden) is complex and difficult to sample from.