I gave a talk on the workshop on how the synthesis of logic and machine Studying, Specifically areas for instance statistical relational Understanding, can help interpretability.
Weighted model counting frequently assumes that weights are only specified on literals, frequently necessitating the need to introduce auxillary variables. We think about a new approach based on psuedo-Boolean capabilities, resulting in a more general definition. Empirically, we also get SOTA results.
Will be Talking on the AIUK function on ideas and practice of interpretability in equipment learning.
I attended the SML workshop inside the Black Forest, and mentioned the connections concerning explainable AI and statistical relational Mastering.
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 modern NeurIPS paper in Glasgow although also covering other techniques for the intersection of logic, Understanding and tractability. Thanks to Oana with the invitation.
The situation we deal with is how the training need to be described when There's missing or incomplete knowledge, bringing about an account according to imprecise probabilities. Preprint below.
A journal paper has long been recognized on prior constraints in tractable https://vaishakbelle.com/ probabilistic products, readily available to the papers tab. Congratulations Giannis!
A the latest collaboration Together with the NatWest Group on explainable machine Mastering is talked about in The Scotsman. Backlink to post in this article. A preprint on the outcome will be manufactured accessible shortly.
Together with colleagues from Edinburgh and Herriot Watt, We've place out the demand a different research agenda.
For the University of Edinburgh, he directs a research lab on synthetic intelligence, specialising within the unification of logic and equipment Understanding, with a new emphasis on explainability and ethics.
The paper discusses how to deal with nested capabilities and quantification in relational probabilistic graphical versions.
I gave an invited tutorial the Bath CDT Art-AI. I lined latest traits and long term developments on explainable device Finding out.
Convention hyperlink Our Focus on symbolically interpreting variational autoencoders, in addition to a new learnability for SMT (satisfiability modulo concept) formulation obtained acknowledged at ECAI.