News for hackers. Stuff that matters.
Re:Ersatz - Deep neural networks in the cloud by ninjin on Thursday January 17, 2013 @06:03PM (#5075817)
I agree that the hyper-parameter selection is a huge pain, personally though, I am more familiar with the work of Snoek et al. [1] from NIPS in December last year. He even distributes a neat Python package that will perform Bayesian optimisation combined with MCMC [2] so that even people, like me, that are not yet familiar with Gaussian Processes can deploy it easily.

[1]: http://arxiv.org/pdf/1206.2944v2

[2]: http://www.cs.toronto.edu/~jasper/software.html

There are no comments on this comment yet.