Maximum Likelihood Inference for Log-linear Models Subject to Constraints of Double Monotone Dependence.
Manuela CazzaroRoberto ColombiPublished in: Stat. Methods Appl. (2006)
Keyphrases
- maximum likelihood
- log linear models
- log linear
- mixture model
- discriminative training
- efficient learning
- parameter learning
- parameter estimation
- em algorithm
- bayesian networks
- expectation maximization
- maximum a posteriori
- markov networks
- information retrieval
- topic models
- belief networks
- boolean functions
- multi class
- pairwise
- similarity measure
- image segmentation