Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning

Robert Peharz, Antonio Vergari, Karl Stelzner, Alejandro Molina, Martin Trapp, Xiaoting Shao, Kristian Kersting, Zoubin Ghahramani

Abstract

Sum-product networks (SPNs) are expressive probabilistic models with a rich set of exact and efficient inference routines. However, in order to guarantee exact inference, they require specific stru...
BibTeX
@inproceedings{peharz2019random,
  author = {Robert Peharz and Antonio Vergari and Karl Stelzner and Alejandro Molina and Martin Trapp and Xiaoting Shao and Kristian Kersting and Zoubin Ghahramani},
  title = {{Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning}},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year = {2019},
}

Loading related content...

Figure