### Resumen

Copyright © PMLR 2017. All rights reserved. Sum-product networks are a relatively new and increasingly popular class of (precise) probabilistic graphical models that allow for marginal inference with polynomial effort. As with other probabilistic models, sum-product networks are often learned from data and used to perform classification. Hence, their results are prone to be unreliable and overconfident. In this work, we develop credal sum-product networks, an imprecise extension of sum-product networks. We present algorithms and complexity results for common inference tasks. We apply our algorithms on realistic classification task using images of digits and show that credal sum-product networks obtained by a perturbation of the parameters of learned sum-product networks are able to distinguish between reliable and unreliable classifications with high accuracy.

Idioma original | Inglés estadounidense |
---|---|

Páginas | 205-216 |

Número de páginas | 12 |

Estado | Publicada - 1 ene 2019 |

Publicado de forma externa | Sí |

Evento | Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017 - Duración: 1 ene 2019 → … |

### Conferencia

Conferencia | Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017 |
---|---|

Período | 1/01/19 → … |

## Huella Profundice en los temas de investigación de 'Credal sum-product networks'. En conjunto forman una huella única.

## Citar esto

Mauá, D. D., Cozman, F. G., Conaty, D., & De Campos, C. P. (2019).

*Credal sum-product networks*. 205-216. Papel presentado en Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017, .