It studies how representations in these logics behave in the dynamic setting, and introduces operators for cutting down a query after steps to an initial state, or updating the representation from those actions.
Interested in synthesizing the semantics of programming languages? We now have a whole new paper on that, recognized at OOPSLA.
I gave a talk entitled "Views on Explainable AI," at an interdisciplinary workshop specializing in making rely on in AI.
If you're attending NeurIPS this 12 months, you might be interested in testing our papers that contact on morality, causality, and interpretability. Preprints can be found within the workshop site.
Gave a chat this Monday in Edinburgh on the principles & follow of device learning, covering motivations & insights from our study paper. Key concerns raised integrated, how you can: extract intelligible explanations + modify the model to fit altering requirements.
I gave a talk on our recent NeurIPS paper in Glasgow while also masking other techniques with the intersection of logic, learning and tractability. As a result of Oana to the invitation.
We have now a whole new paper accepted on Understanding exceptional linear programming goals. We acquire an “implicit“ hypothesis building solution that yields good theoretical bounds. Congrats to Gini and Alex on acquiring this paper acknowledged. Preprint here.
The post introduces a common logical framework for reasoning about discrete and continuous probabilistic models in dynamical domains.
We analyze arranging in relational Markov decision processes involving discrete and continuous states and steps, and an unknown range of objects (through probabilistic programming).
From the paper, we exploit the XADD information https://vaishakbelle.com/ construction to conduct probabilistic inference in blended discrete-continual spaces efficiently.
He has served within the senior software committee/place chair of big AI conferences, co-chaired the ML observe at KR, amid Other individuals, and as PI and CoI secured a grant cash flow of near to 8 million pounds.
Our MLJ (2017) post on scheduling with hybrid MDPs was approved for presentation in the journal observe.
The very first introduces a primary-get language for reasoning about probabilities in dynamical domains, and the second considers the automated fixing of chance issues specified in purely natural language.
Conference hyperlink Our work on symbolically interpreting variational autoencoders, in addition to a new learnability for SMT (satisfiability modulo principle) formulation acquired acknowledged at ECAI.