Sum-Product Networks: A New Deep Architecture

Details Sum-Product Networks: A New Deep Architecture Sum-Product Networks: A New Deep Architecture

2012-02-14

arxiv.org/abs/1202.3732v1

Computer Science

Learning

Scientific paper

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. Essentially all tractable graphical models can be cast as SPNs, but SPNs are also strictly more general. We then propose learning algorithms for SPNs, based on backpropagation and EM. Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks. For example, SPNs perform image completion better than state-of-the-art deep networks for this task. SPNs also have intriguing potential connections to the architecture of the cortex.

Affiliated with

Also associated with

No associations

Rating

Sum-Product Networks: A New Deep Architecture does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Sum-Product Networks: A New Deep Architecture, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sum-Product Networks: A New Deep Architecture will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-90500