Approximate inference
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
- Variational Bayesian methods
- Markov chain Monte Carlo
- Expectation propagation
- Markov random fields
- Bayesian networks
- Loopy and generalized belief propagation
gollark: ```cint[5] five_ints() { int ints[5] = {1, 2, 3, 4, 5}; return ints;}int main() { int ints[5] = five_ints(); printf("%d", ints[0]);}```
gollark: My WiFi connection is *particularly* filled with bees today, wow.
gollark: Oh, it has, yes.
gollark: You can use haskell vectoroids.
gollark: GTech™ cryoapionic conceptual chemists determined that C arrays have a fairly low pH and are thus not based.
See also
References
- "Approximate Inference and Constrained Optimization". Uncertainty in Artificial Intelligence - UAI: 313–320. 2003.
- "Approximate Inference". Retrieved 2013-07-15.
External links
- Tom Minka, Microsoft Research (Nov 2, 2009). "Machine Learning Summer School (MLSS), Cambridge 2009, Approximate Inference" (video lecture).
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.