Search Results for author:
Found 4 papers, 0 papers with code
Evolutionary Expectation Maximization for Generative Models with Binary Latents
In general we believe that, with the link established here, standard as well as recent results in the field of evolutionary optimization can be leveraged to address the difficult problem of parameter optimization in generative models.
GP-select: Accelerating EM using adaptive subspace preselection
We propose a nonparametric procedure to achieve fast inference in generative graphical models when the number of latent states is very large.
Select and Sample - A Model of Efficient Neural Inference and Learning
We demonstrate the effectiveness and efficiency of this approach on a sparse coding model.
The Maximal Causes of Natural Scenes are Edge Filters
In applications to image patches we find that Gabor-like basis functions are obtained.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
