Neural Variational Inference and Learning in Belief Networks — mentioned by mrdrozdov

Tue, 22 Mar 2016 17:43:00 GMT

Here's the abstract from the paper: Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast non-iterative approximate inference method that uses a feedforward network to implement efficient exact sampling from the variational posterior. The model and this inference network are trained jointly by maximizing a variational lower bound on the log-likelihood. Although the naive…

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

Neural Variational Inference and Learning in Belief Networks · HackerPapers discussions

Neural Variational Inference and Learning in Belief Networks — mentioned by mrdrozdov