ReGROUND - Deep models and probabilistic logic programming,

- Deniz Yuret (Koc University) Using deep models for grounded language learning

We will introduce the model architecture and training infrastructure used in our project to create grounded language learning systems that learn from instruction-perception-action examples.

- Alessandro Saffiotti, Amy Loutfi and Andreas Persson

Perceptual Anchoring of Objects

- Luc De Raedt (KULeuven) Probabilistic logic programming and its applications

Probabilistic programs combine the power of programming languages with that of probabilistic graphical models. There has been a lot of progress in this paradigm over the past twenty years. This talk will introduce probabilistic logic programming languages, which are based on Sato's distribution semantics and which extend probabilistic databases. The key idea is that facts or tuples can be annotated with probabilities that indicate their degree of belief. Together with the rules that encode domain knowledge they induce a set of possible worlds. After an introduction to probabilistic programs, which will cover semantics, inference, and learning, the talk will sketch some emerging applications in knowledge based systems, in cognitive robotics, in grounded language learning and in answering probability questions.