DRAW: A Recurrent Neural Network For Image Generation · HackerPapers discussions

DRAW: A Recurrent Neural Network For Image Generation — mentioned by 0-_-0

Thu, 20 Feb 2020 13:07:35 GMT

> But much more interesting to me is a lossless domain-specific compressor, which I’m not aware of any examples of. (Please tell me if about some if you know them!) A bit academic, but if you check out this paper from 2015 https://arxiv.org/pdf/1502.04623.pdf on a neural network trained on binarised MNIST (28x28 pixel images), Table 2 quotes entropy figures of 116.815 after converting to bits, which would be 28*28/116.815=6.71x compression (if used as a compressor)

Paper and discussion history. A mention is not an endorsement.

DRAW: A Recurrent Neural Network For Image Generation — mentioned by nl

Fri, 30 Sep 2016 05:28:46 GMT

Expecting 2 years of research by around 20 of the best DNN researchers on the planet to be compressed into a StackOverflow answer before it has been done seems a fairly large amount to expect. Not a huge fan of the negativity on StackOverflow, but until August 2016 (when the paper this was based on was published - or maybe 2015, with DRAW[2]) people actively working in this area didn't think it was possible. Also, the single answer there certainly didn't say anything like it was a stupid idea. I don't think the author of that answer knew much about autoencoders. Also^2, your question isn't…

Paper and discussion history. A mention is not an endorsement.

DRAW: A Recurrent Neural Network For Image Generation — mentioned by themann9

Mon, 07 Sep 2015 04:59:27 GMT

Guy, the only thing abundantly clear is that you are full of dung. Your shameless self-promotion may piss-off the police chief here - murbard2, so be more careful. Ten digits better classified, out of 10000? With a structure more complicated than a human DNA vs two lines of code? Congratulations! Or, and how are your "stairways-to-heaven" even remotely universal? Show us something these networks have generated like the VAE or Gibbs/ACE papers? Perhaps you can show some density estimation results as in http://arxiv.org/abs/1502.04623 or http://arxiv.org/abs/1508.06585? Oja and Hyvarinen are…

Paper and discussion history. A mention is not an endorsement.

DRAW: A Recurrent Neural Network For Image Generation — HN submission

Sat, 28 Feb 2015 20:53:39 GMT

DRAW: A Recurrent Neural Network for Image Generation [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

DRAW: A Recurrent Neural Network For Image Generation — HN submission

Tue, 17 Feb 2015 15:17:02 GMT

DRAW: A Recurrent Neural Network For Image Generation [pdf]

26 points; 7 discussion replies on HN. Paper and source history. A submission is not an endorsement.