I gave a talk within the workshop on how the synthesis of logic and device Finding out, Particularly spots for instance statistical relational Studying, can empower interpretability.
Weighted model counting often assumes that weights are only specified on literals, often necessitating the necessity to introduce auxillary variables. We take into consideration a new approach based on psuedo-Boolean capabilities, bringing about a more common definition. Empirically, we also get SOTA outcomes.
The Lab carries out investigate in synthetic intelligence, by unifying Understanding and logic, having a the latest emphasis on explainability
I attended the SML workshop inside the Black Forest, and mentioned the connections amongst explainable AI and statistical relational Understanding.
Our paper (joint with Amelie Levray) on Discovering credal sum-solution networks has actually been recognized to AKBC. This kind of networks, as well as other sorts of probabilistic circuits, are appealing as they warranty that particular sorts of chance estimation queries can be computed in time linear in the size from the network.
The posting, to seem within the Biochemist, surveys a lot of the motivations and techniques for building AI interpretable and accountable.
Keen on schooling neural networks with sensible constraints? We have a brand new paper that aims in the direction of total fulfillment of Boolean and linear arithmetic constraints on education at AAAI-2022. Congrats to Nick and Rafael!
The write-up introduces a standard rational framework for reasoning about discrete and steady probabilistic models in dynamical domains.
We research planning in relational Markov conclusion processes involving discrete and continual states and actions, and an unidentified range of objects (through probabilistic programming).
While in the paper, we exploit the XADD details structure to carry out probabilistic inference in combined discrete-ongoing Areas competently.
Paulius' work on algorithmic approaches for randomly creating logic packages and probabilistic logic packages has become approved for the ideas and practise of constraint programming (CP2020).
Our MLJ (2017) report on planning with hybrid MDPs was acknowledged for presentation within the journal monitor.
Our work on synthesizing strategies with loops from the existence of sound will show up from the Intercontinental journal of approximate reasoning.
Our paper on synthesizing plans with loops in the existence of probabilistic sounds, recognized the journal of approximate reasoning, has also been approved on https://vaishakbelle.com/ the ICAPS journal observe. Preprint to the total paper listed here.