A Mean Field Learning Algorithm for Unsupervised Neural Networks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The frontier of simulation-based inference (2019, methodology): “This challenge is commonly addressed with Markov Chain Monte Carlo (MCMC) methods (10, 11) or variational inference (VI) (12).”
Learning with Mixtures of Trees (2000, background): “For u, v ∈ V and (u, v) ∈ E, let T uv denote a joint probability distribution on u and v.”
Non-conjugate Variational Message Passing for Multinomial and Binary Regression (2011, background): “The second line of work applying VB to non-conjugate models involves deriving lower bounds to approximate the expectations [9, 18, 5, 10, 11] required to calculate the KL divergence.”
Constituent Parsing with Incremental Sigmoid Belief Networks (2007, methodology): “However, in our case of dynamic graphical models, we have to use a different approach which allows us to construct an incremental parsing method without needing to introduce the additional parameters proposed in (Saul and Jordan, 1999).”
An Introduction to Variational Methods for Graphical Models (1999, methodology): “In this case it is again readily shown that the time complexity is exponential in K . We will not discuss the higherorder HMM further in this paper; for a variational algorithm for the higher-order HMM see Saul and Jordan (1996) .”