Encapsulating models and approximate inference programs in probabilistic modules.
Marco F. Cusumano-TownerVikash K. MansinghkaPublished in: CoRR (2016)
Keyphrases
- approximate inference
- probabilistic model
- graphical models
- factor graphs
- bayesian networks
- parameter estimation
- variational methods
- belief propagation
- message passing
- exact inference
- structured prediction
- computer vision
- linear gaussian
- dynamic bayesian networks
- conditional probabilities
- semi supervised
- loopy belief propagation
- expectation propagation
- markov chain monte carlo
- active learning
- prior knowledge
- support vector
- clustering algorithm
- information retrieval