News for hackers. Stuff that matters.

A comment on Improved Techniques for Training GANs – OpenAI's first paper. Parent comment

Re:Improved Techniques for Training GANs – OpenAI's first paper by T-A on Tuesday June 14, 2016 @01:57PM (#11903914)
> the one-shot learning paper coming out of (I've forgotten!!) where the authors are famously doubtful about the utility of Deep Learning

This? https://www.technologyreview.com/s/544376/this-ai-algorithm-...

http://cims.nyu.edu/~brenden/LakeEtAl2015Science.pdf

[ Parent | on HN ]
Re:Improved Techniques for Training GANs – OpenAI's first paper by nl on Tuesday June 14, 2016 @10:06PM (#11906774)
That was it, although I see I've conflated the views of Gary Marcus (who I think it is fair to characterize as anti-Deep Learning[1]) and Lake, Salakhutdinov, and Tenenbaum who wrote the paper.

[1] https://www.technologyreview.com/s/544606/can-this-man-make-...

[ Parent | on HN ]