Approximate inference

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

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[edit]

[1][2]

See also[edit]

References[edit]

  1. ^ "Approximate Inference and Constrained Optimization". Uncertainty in Artificial Intelligence - UAI: 313–320. 2003.
  2. ^ "Approximate Inference". Retrieved 2013-07-15.

External links[edit]