However,DBNsonly allow for a fixed chain of Markov dependencies between time slices and cannot represent nested hierarchicalstructures.

Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but alsosentence-levelstochastic temporaltransitions.

We analyze the complexity of learning directed acyclic graphical models from observational dataingeneral settings without specific distributional assumptions.

This paper introduces deep synoptic Monte Carlo planning (DSMCP) for large imperfect information games.