Unifying Sum Product Networks and Submodular Fields
Proceedings of the Workshop on Principled Approaches to Deep Learning at ICML, 2017.
Sum-product networks (SPNs) are a relatively new class of deep probabilistic models that are expressive but also tractable, due in part to their ability to exploit local structure in the form of context-specific independence and determinism. However, there remain many types of problems that are highly structured, but for which SPNs are in...More
Full Text (Upload PDF)
PPT (Upload PPT)