Sum-Product Networks: A New Deep Architecture

UAI 2011 pp. 337-346

doi:10.1109/ICCVW.2011.6130310 /uai/2011/poon2011uai-sum/

Abstract

The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are the most 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) and will present in this abstract.

PDF UAI Semantic Scholar

Cite

Text

Poon and Domingos. "Sum-Product Networks: A New Deep Architecture." Conference on Uncertainty in Artificial Intelligence, 2011. doi:10.1109/ICCVW.2011.6130310

Markdown

[Poon and Domingos. "Sum-Product Networks: A New Deep Architecture." Conference on Uncertainty in Artificial Intelligence, 2011.](https://mlanthology.org/uai/2011/poon2011uai-sum/) doi:10.1109/ICCVW.2011.6130310

BibTeX

@inproceedings{poon2011uai-sum,
  title     = {{Sum-Product Networks: A New Deep Architecture}},
  author    = {Poon, Hoifung and Domingos, Pedro M.},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2011},
  pages     = {337-346},
  doi       = {10.1109/ICCVW.2011.6130310},
  url       = {https://mlanthology.org/uai/2011/poon2011uai-sum/}
}