Tree-structured probabilistic models admit simple, fast inference. However, they are not well suited to phenomena such as occlusion, where multiple components of an object may dis...
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
Background: DNA replication is a fundamental biological process during S phase of cell division. It is initiated from several hundreds of origins along whole chromosome with diffe...
A hypergraph is a generalization of the traditional graph in which the edges are arbitrary non-empty subsets of the vertex set. It has been applied successfully to capture highord...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...