Drew, Dave, Larissa and I experienced the chance to talk about the motivatons and foundations for instigating The brand new research theme of Experiential AI in a very ninety moment discuss.
Previous 7 days, I gave a chat on the pint of science on automatic units and their effect, touching on the subjects of fairness and blameworthiness.
Will probably be speaking within the AIUK party on concepts and exercise of interpretability in device Understanding.
For anyone who is attending NeurIPS this yr, you might have an interest in checking out our papers that contact on morality, causality, and interpretability. Preprints are available about the workshop webpage.
Our paper (joint with Amelie Levray) on Finding out credal sum-product networks has become recognized to AKBC. This sort of networks, coupled with other types of probabilistic circuits, are interesting simply because they warranty that particular forms of chance estimation queries may be computed in time linear in the size from the community.
A consortia undertaking on trustworthy methods and goverance was recognized late past 12 months. News url right here.
Now we have a fresh paper recognized on Understanding best linear programming objectives. We get an “implicit“ speculation design solution that yields great theoretical bounds. Congrats to Gini and Alex on receiving this paper recognized. Preprint right here.
A journal paper has become acknowledged on prior constraints in tractable probabilistic styles, readily available to the papers tab. Congratulations Giannis!
A current collaboration with the NatWest Team on explainable device Understanding is talked about inside the Scotsman. Link to posting listed here. A preprint on the outcome will likely be produced out https://vaishakbelle.com/ there Soon.
Together with colleagues from Edinburgh and Herriot Watt, We now have set out the call for a different study agenda.
Paulius' work on algorithmic techniques for randomly creating logic systems and probabilistic logic courses has been accepted towards the ideas and practise of constraint programming (CP2020).
Our MLJ (2017) short article on organizing with hybrid MDPs was recognized for presentation with the journal track.
Our work on synthesizing options with loops in the presence of noise will appear within the Worldwide journal of approximate reasoning.
Conference website link Our work on symbolically interpreting variational autoencoders, as well as a new learnability for SMT (satisfiability modulo theory) formulas bought recognized at ECAI.