Sum-Product Networks: A New Deep Architecture

Understand

The key limiting factor in graphical model inference and learning is the complexity of the partition function.

• We thus ask the question: what are general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sum-product networks (SPNs).
• SPNs are directed acyclic graphs with variables as leaves, sums and products as internal nodes, and weighted edges.
• We show that if an SPN is complete and consistent it represents the partition function and all marginals of some graphical model, and give semantics to its nodes.