I gave a talk, entitled "Explainability being a service", at the above occasion that reviewed anticipations regarding explainable AI and how may be enabled in apps.
Weighted product counting typically assumes that weights are only specified on literals, usually necessitating the necessity to introduce auxillary variables. We look at a whole new method based on psuedo-Boolean features, leading to a far more common definition. Empirically, we also get SOTA success.
The paper tackles unsupervised application induction above blended discrete-continuous facts, and is acknowledged at ILP.
The paper discusses the epistemic formalisation of generalised scheduling within the presence of noisy acting and sensing.
Gave a chat this Monday in Edinburgh to the ideas & apply of equipment Mastering, covering motivations & insights from our study paper. Essential queries lifted involved, the way to: extract intelligible explanations + modify the design to fit shifting needs.
I gave a talk on our new NeurIPS paper in Glasgow even though also covering other strategies with the intersection of logic, Understanding and tractability. Thanks to Oana to the invitation.
We have a whole new paper recognized on learning ideal linear programming aims. We choose an “implicit“ hypothesis building technique that yields awesome theoretical bounds. Congrats to Gini and Alex on getting this paper acknowledged. Preprint listed here.
I gave a seminar on extending the expressiveness of probabilistic relational products with initial-purchase functions, for instance common quantification in excess of infinite domains.
Lately, he https://vaishakbelle.com/ has consulted with important financial institutions on explainable AI and its influence in economical institutions.
Within the paper, we exploit the XADD info composition to perform probabilistic inference in combined discrete-ongoing Areas efficiently.
Paulius' Focus on algorithmic techniques for randomly creating logic plans and probabilistic logic applications has become acknowledged towards the principles and practise of constraint programming (CP2020).
Our MLJ (2017) posting on preparing with hybrid MDPs was acknowledged for presentation for the journal track.
When you are attending AAAI this calendar year, it's possible you'll have an interest in trying out our papers that contact on fairness, abstraction and generalized sum-merchandise difficulties.
I gave a chat around the challenges of artificial intelligence and investigate priorities with the International Progress Society.