This paper considers the computational power of constant size, dynamic Bayesian networks. Although discrete dynamic Bayesian networks are no more powerful than hidden Markov models, dynamic Bayesian networks with continuous random variables and discrete children of continuous parents are capable of performing Turing-complete computation. With modified versions of existing algorithms for belief ...

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan is featured for its deep root into Bayesia...

Refineries are highly complex installations and a potential source of major hazards. Due to the large volumes flammable toxic substances present, an accident in refinery may have multidimensional consequences. This includes severe property damages, injuries personnel, releases chemicals causing adverse health effects on nearby residents environment, business interruption losses that lead compan...

Bayesian Belief Networks provide a principled, mathematically sound, and logically rational mechanism to represent student models. The belief net backbone structure proposed by Reye [14,15] offers a practical way to represent and update Bayesian student models describing both cognitive and social aspects of the learner. Considering students as active participants in the modelling process, this ...

The fuzzy belief Petri net we propose in this paper propagates fuzzy beliefs from observations at nodes that represent measured parameters to fuzzy beliefs of the truths of parameters at hidden and decision nodes. The fuzzy influences spread from the observation nodes throughout our new enhanced bidirectional fuzzy belief Petri net. Compared with Bayesian belief networks, it is simpler and fast...