Drew, Dave, Larissa and I experienced the chance to talk about the motivatons and foundations for instigating the new exploration topic of Experiential AI inside a 90 moment communicate.
Last week, I gave a talk in the pint of science on automated programs and their affect, concerning the matters of fairness and blameworthiness.
The paper tackles unsupervised application induction in excess of mixed discrete-ongoing info, and is particularly approved at ILP.
He has made a occupation outside of performing investigation on the science and technological innovation of AI. He has posted close to 120 peer-reviewed content, received very best paper awards, and consulted with financial institutions on explainability. As PI and CoI, he has secured a grant money of near 8 million pounds.
An article within the setting up and inference workshop at AAAI-18 compares two distinct strategies for probabilistic setting up via probabilistic programming.
I gave a talk on our recent NeurIPS paper in Glasgow while also masking other methods at the intersection of logic, learning and tractability. As a result of Oana to the invitation.
Thinking about education neural networks with reasonable constraints? Now we have a new paper that aims in the direction of entire gratification of Boolean and linear arithmetic constraints on schooling at AAAI-2022. Congrats to Nick and Rafael!
Bjorn And that i are promoting a 2 calendar year postdoc on integrating causality, reasoning and know-how graphs for misinformation detection. See listed here.
Website link In the final 7 days of October, I gave a chat informally talking about explainability and moral accountability in artificial intelligence. Due to the organizers https://vaishakbelle.com/ for that invitation.
Along with colleagues from Edinburgh and Herriot Watt, We've got set out the demand a brand new exploration agenda.
He has served on the senior plan committee/region chair of significant AI conferences, co-chaired the ML track at KR, among Other people, and as PI and CoI secured a grant income of near eight million lbs ..
A journal paper on abstracting probabilistic types continues to be approved. The paper research the semantic constraints that enables one to abstract a posh, low-degree product with an easier, large-amount 1.
I gave an invited tutorial the Tub CDT Artwork-AI. I included present developments and long run traits on explainable machine Studying.
Meeting backlink Our work on symbolically interpreting variational autoencoders, as well as a new learnability for SMT (satisfiability modulo idea) formulation acquired acknowledged at ECAI.