I gave a chat in the workshop on how the synthesis of logic and device Finding out, Specifically areas which include statistical relational Finding out, can enable interpretability.
I are going to be supplying a tutorial on logic and Discovering which has a focus on infinite domains at this calendar year's SUM. Connection to party in this article.
I gave a chat entitled "Perspectives on Explainable AI," at an interdisciplinary workshop specializing in making have faith in in AI.
I attended the SML workshop during the Black Forest, and discussed the connections between explainable AI and statistical relational Finding out.
Gave a talk this Monday in Edinburgh to the concepts & apply of equipment Finding out, covering motivations & insights from our survey paper. Key issues raised involved, the best way to: extract intelligible explanations + modify the product to fit transforming wants.
A consortia task on trusted methods and goverance was acknowledged late very last calendar year. Information hyperlink listed here.
Keen on education neural networks with rational constraints? We have a completely new paper that aims toward total satisfaction of Boolean and linear arithmetic constraints on teaching at AAAI-2022. Congrats to Nick and Rafael!
Bjorn And that i are promoting a 2 12 months postdoc on integrating causality, reasoning and understanding graphs for misinformation detection. See in this article.
We study organizing in relational Markov conclusion processes involving discrete and constant states and steps, and an not known quantity of objects (through probabilistic programming).
Jonathan’s paper considers a lifted approached to weighted design integration, together with circuit construction. Paulius’ paper develops a measure-theoretic perspective on weighted model counting and proposes a method to encode conditional weights on literals analogously to conditional probabilities, which ends up in important general performance advancements.
Paulius' work on algorithmic strategies for randomly building logic courses and probabilistic logic systems has become acknowledged towards the concepts and practise of constraint programming (CP2020).
The framework is relevant to a big course of formalisms, such as probabilistic relational styles. The paper also research the synthesis challenge in that context. Preprint here.
I gave an invited tutorial the Tub CDT Art-AI. I protected latest traits and future trends on explainable machine Studying.
Meeting url Our work on symbolically interpreting variational autoencoders, in addition to a new learnability for https://vaishakbelle.com/ SMT (satisfiability modulo concept) formulation obtained acknowledged at ECAI.