Fabrizio Riguzzi (Department of Mathematics and Computer Science, University of Ferrara)
February 28th, 2018 – 12:00 AM
DIISM, Artificial Intelligence laboratory (room 201), Siena SI
Probabilistic logic programming (PLP) under the distribution semantics handles well relational uncertain data and knwoledge graphs.
However, inference is expensive inference so simplified versions of the language have been explored to speed up learning algorithms.
One version, called hierarchical PLP makes the language truth-functional and inference reduces to the evaluation of formulas in the product fuzzy logic.
Programs in this language can also be seen as arithmetic circuits or deep neural networks and inference can be reperformed quickly when the parameters change. Learning can then be performed by EM or backpropagation. The talk will illustrate hierarchical PLP and discuss relationships with alternative formalisms for neural-symbolic integration.