I gave a chat at the workshop on how the synthesis of logic and device Studying, In particular locations for instance statistical relational learning, can allow interpretability.
I will likely be giving a tutorial on logic and learning which has a center on infinite domains at this 12 months's SUM. Website link to event in this article.
Will probably be Talking on the AIUK party on ideas and observe of interpretability in device Discovering.
For anyone who is attending NeurIPS this year, you could possibly have an interest in checking out our papers that touch on morality, causality, and interpretability. Preprints can be found about the workshop web site.
Our paper (joint with Amelie Levray) on Mastering credal sum-products networks has been accepted to AKBC. This kind of networks, in addition to other types of probabilistic circuits, are appealing simply because they ensure that specific varieties of likelihood estimation queries may be computed in time linear in the size of the community.
I gave a talk on our the latest NeurIPS paper in Glasgow although also masking other ways at the intersection of logic, Finding out and tractability. Due to Oana for that invitation.
The condition we tackle is how the educational must be outlined when There may be lacking or incomplete details, bringing about an account based on imprecise probabilities. Preprint here.
A journal paper has become acknowledged on prior constraints in tractable probabilistic designs, accessible on the papers tab. Congratulations Giannis!
A new collaboration Together with the NatWest Group on explainable equipment Understanding is discussed from the Scotsman. Website link to article below. A preprint on the outcomes are going to be manufactured accessible Soon.
Jonathan’s paper considers a lifted approached to weighted design integration, together with circuit building. Paulius’ paper develops a evaluate-theoretic standpoint on weighted model counting and proposes a method to encode conditional weights on literals analogously to conditional probabilities, which results in significant effectiveness improvements.
Paulius' work on algorithmic methods for randomly creating logic packages and probabilistic logic courses has long been recognized towards the rules and practise of constraint programming (CP2020).
The framework is relevant to a big course of formalisms, like probabilistic relational designs. The paper also experiments the synthesis dilemma in that context. Preprint here.
In case you are attending AAAI this yr, it's possible you'll have an interest in checking out our papers that touch on fairness, abstraction and generalized sum-product troubles.
Our paper on synthesizing options with loops during the existence of probabilistic sounds, recognized the journal of approximate reasoning, has also been recognized into the ICAPS journal track. Preprint to https://vaishakbelle.com/ the entire paper in this article.