I gave a talk at the workshop on how the synthesis of logic and machine Finding out, In particular spots such as statistical relational learning, can permit interpretability.
Enthusiastic about synthesizing the semantics of programming languages? We've a whole new paper on that, approved at OOPSLA.
The paper tackles unsupervised software induction in excess of combined discrete-steady data, and is approved at ILP.
The paper discusses the epistemic formalisation of generalised planning from the presence of noisy acting and sensing.
Our paper (joint with Amelie Levray) on Understanding credal sum-product or service networks has been accepted to AKBC. This sort of networks, in conjunction with other sorts of probabilistic circuits, are interesting because they assure that specific forms of likelihood estimation queries might be computed in time linear in the dimensions with the community.
The write-up, to look while in the Biochemist, surveys a number of the motivations and strategies for generating AI interpretable and responsible.
Serious about training neural networks with sensible constraints? We have a new paper that aims towards full satisfaction of Boolean and linear arithmetic constraints on training at AAAI-2022. Congrats to Nick and Rafael!
The posting introduces a normal rational framework for reasoning about discrete and steady probabilistic models in dynamical domains.
A recent collaboration While using the NatWest Group on explainable equipment Finding out is mentioned in The Scotsman. Backlink to write-up here. A preprint on the final results will probably be built offered Soon.
Together with colleagues from Edinburgh and Herriot Watt, We have now set out the demand a new analysis agenda.
At the College of Edinburgh, he directs a study lab on synthetic intelligence, specialising inside the unification of logic and equipment Finding out, having a the latest emphasis on explainability and ethics.
The framework is applicable to a considerable class of formalisms, which include probabilistic relational designs. The paper also experiments the synthesis difficulty in that context. Preprint in this article.
For anyone who is attending AAAI this calendar year, you might be interested in looking at https://vaishakbelle.com/ our papers that touch on fairness, abstraction and generalized sum-solution troubles.
I gave a chat about the dangers of synthetic intelligence and exploration priorities for the Worldwide Advancement Modern society.