We introduce a recurrent architecture having a modular structure and we formulate a training procedure based on the EM algorithm. The resulting model has similarities to hidden Ma...
In this paper we present decomposable priors, a family of priors over structure and parameters of tree belief nets for which Bayesian learning with complete observations is tracta...
In this paper, we survey the current state-ofart models for structured learning problems, including Hidden Markov Model (HMM), Conditional Random Fields (CRF), Averaged Perceptron...
Markov decisionprocesses(MDPs) haveproven to be popular models for decision-theoretic planning, but standard dynamic programming algorithms for solving MDPs rely on explicit, stat...
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...