I gave a talk for the workshop on how the synthesis of logic and device Finding out, Specifically areas for instance statistical relational Studying, can empower interpretability.
Weighted product counting generally assumes that weights are only specified on literals, typically necessitating the need to introduce auxillary variables. We contemplate a fresh method according to psuedo-Boolean functions, bringing about a more common definition. Empirically, we also get SOTA results.
The Lab carries out study in synthetic intelligence, by unifying Finding out and logic, having a the latest emphasis on explainability
I attended the SML workshop during the Black Forest, and discussed the connections between explainable AI and statistical relational Discovering.
An write-up in the planning and inference workshop at AAAI-eighteen compares two unique approaches for probabilistic scheduling by the use of probabilistic programming.
I gave a talk on our current NeurIPS paper in Glasgow though also masking other methods within the intersection of logic, Mastering and tractability. Because of Oana for the invitation.
The trouble we deal with is how the training needs to be described when There's lacking or incomplete details, leading to an account determined by imprecise probabilities. Preprint here.
A journal paper is approved on prior constraints in tractable probabilistic styles, out there on the papers tab. Congratulations Giannis!
A latest collaboration with the NatWest Team on explainable machine Mastering is mentioned in The Scotsman. Backlink to report here. A preprint on the final results will probably be built offered Soon.
Jonathan’s paper considers a lifted approached to weighted design integration, including circuit building. Paulius’ paper develops a measure-theoretic standpoint on weighted model counting and proposes a method to encode conditional weights on literals analogously to conditional probabilities, which results in substantial effectiveness advancements.
Paulius' work on algorithmic strategies for randomly generating logic applications and probabilistic logic applications is acknowledged towards the principles and practise of constraint programming (CP2020).
The framework https://vaishakbelle.com/ is applicable to a considerable class of formalisms, which include probabilistic relational designs. The paper also experiments the synthesis dilemma in that context. Preprint here.
For anyone who is attending AAAI this calendar year, you might be interested in checking out our papers that touch on fairness, abstraction and generalized sum-item difficulties.
Our paper on synthesizing options with loops during the existence of probabilistic sound, approved the journal of approximate reasoning, has also been approved to your ICAPS journal keep track of. Preprint to the entire paper in this article.