I gave a chat at the workshop on how the synthesis of logic and equipment Discovering, In particular locations such as statistical relational Finding out, can enable interpretability.
Weighted product counting generally assumes that weights are only specified on literals, generally necessitating the necessity to introduce auxillary variables. We take into account a whole new technique depending on psuedo-Boolean functions, bringing about a far more standard definition. Empirically, we also get SOTA final results.
The Lab carries out exploration in artificial intelligence, by unifying Discovering and logic, that has a latest emphasis on explainability
The paper discusses the epistemic formalisation of generalised scheduling inside the existence of noisy performing and sensing.
We consider the question of how generalized ideas (ideas with loops) may be deemed correct in unbounded and continuous domains.
A consortia project on honest techniques and goverance was recognized late previous calendar year. News connection listed here.
Serious about training neural networks with logical constraints? We have a new paper that aims towards complete fulfillment of Boolean and linear arithmetic constraints on coaching at AAAI-2022. Congrats to Nick and Rafael!
Bjorn and I are promotion a two year postdoc on integrating causality, reasoning and awareness graphs for misinformation detection. See below.
We research setting up in relational Markov selection procedures involving discrete and continuous states and actions, and an mysterious quantity of objects (by means of probabilistic programming).
In the paper, we exploit the XADD info construction to complete probabilistic inference in blended discrete-ongoing Areas competently.
He has served around the senior program committee/area chair of important AI conferences, co-chaired the ML observe at KR, amid Other individuals, and as PI and CoI secured a grant earnings of near eight million lbs.
Our MLJ (2017) posting on organizing with hybrid MDPs was recognized for presentation in the journal observe.
Our work on synthesizing ideas with loops within the presence of noise will appear within the international journal of approximate reasoning.
Our operate (with Giannis) surveying and https://vaishakbelle.com/ distilling ways to explainability in device Studying continues to be accepted. Preprint in this article, but the ultimate Edition will probably be online and open up accessibility soon.