Approximate inference
From Wikipedia, the free encyclopedia
Approximate inference methods make it possible to learn realistic models from big data by trading off computation time for accuracy, when exact learning and inference are computationally intractable.
Major methods classes
- Laplace's approximation
- Variational Bayesian methods
- Markov chain Monte Carlo
- Expectation propagation
- Markov random fields
- Bayesian networks
- Loopy and generalized belief propagation
See also
References
Page Template:Reflist/styles.css has no content.
- ^ Page Module:Citation/CS1/styles.css has no content."Approximate Inference and Constrained Optimization". Uncertainty in Artificial Intelligence: 313–320. 2003.
- ^ Page Module:Citation/CS1/styles.css has no content."Approximate Inference". Retrieved 2013-07-15.
External links
- Page Module:Citation/CS1/styles.css has no content.Tom Minka, Microsoft Research (Nov 2, 2009). "Machine Learning Summer School (MLSS), Cambridge 2009, Approximate Inference" (video lecture).
