I gave a talk in the workshop on how the synthesis of logic and machine Mastering, Primarily areas like statistical relational Studying, can enable interpretability.
I might be giving a tutorial on logic and Finding out with a target infinite domains at this yr's SUM. Website link to occasion right here.
I gave a talk entitled "Views on Explainable AI," at an interdisciplinary workshop concentrating on developing trust in AI.
The paper discusses the epistemic formalisation of generalised scheduling in the presence of noisy acting and sensing.
We consider the question of how generalized strategies (strategies with loops) might be deemed right in unbounded and continuous domains.
The short article, to appear while in the Biochemist, surveys a number of the motivations and strategies for creating AI interpretable and accountable.
We've got a whole new paper acknowledged on Finding out ideal linear programming goals. We get an “implicit“ hypothesis construction approach that yields nice theoretical bounds. Congrats to Gini and Alex on having this paper recognized. Preprint below.
Bjorn And that i are marketing a two yr postdoc on integrating causality, reasoning and knowledge graphs for misinformation detection. See below.
We review scheduling in relational Markov choice processes involving discrete and constant states and steps, https://vaishakbelle.com/ and an mysterious range of objects (via probabilistic programming).
Along with colleagues from Edinburgh and Herriot Watt, We have now place out the call for a whole new investigation agenda.
Within the University of Edinburgh, he directs a exploration lab on artificial intelligence, specialising while in the unification of logic and equipment Understanding, which has a latest emphasis on explainability and ethics.
A journal paper on abstracting probabilistic versions has actually been recognized. The paper studies the semantic constraints that permits one particular to summary a posh, small-level model with a simpler, large-stage just one.
Our Focus on synthesizing options with loops from the presence of noise will appear in the Intercontinental journal of approximate reasoning.
Our paper on synthesizing designs with loops from the existence of probabilistic noise, accepted the journal of approximate reasoning, has also been recognized on the ICAPS journal monitor. Preprint to the full paper in this article.