I gave a talk within the workshop on how the synthesis of logic and equipment Studying, especially parts including statistical relational learning, can empower interpretability.
Weighted model counting usually assumes that weights are only specified on literals, usually necessitating the need to introduce auxillary variables. We contemplate a fresh strategy depending on psuedo-Boolean functions, bringing about a far more standard definition. Empirically, we also get SOTA benefits.
The paper tackles unsupervised software induction more than blended discrete-constant info, and is recognized at ILP.
The paper discusses the epistemic formalisation of generalised planning in the existence of noisy performing and sensing.
Gave a chat this Monday in Edinburgh to the rules & exercise of equipment Discovering, masking motivations & insights from our study paper. Critical thoughts lifted included, how to: extract intelligible explanations + modify the model to fit shifting demands.
I’ll be providing a chat on the meeting on reasonable and liable AI while in the https://vaishakbelle.com/ cyber Actual physical programs session. Thanks to Ram & Christian for that invitation. Link to function.
The situation we deal with is how the learning needs to be outlined when You can find missing or incomplete data, leading to an account based upon imprecise probabilities. Preprint here.
A journal paper continues to be accepted on prior constraints in tractable probabilistic types, out there over the papers tab. Congratulations Giannis!
Website link In the last week of Oct, I gave a talk informally discussing explainability and moral accountability in artificial intelligence. Thanks to the organizers for the invitation.
From the paper, we exploit the XADD information construction to conduct probabilistic inference in mixed discrete-steady spaces competently.
He has served around the senior plan committee/region chair of main AI conferences, co-chaired the ML observe at KR, among Other people, and as PI and CoI secured a grant revenue of close to eight million kilos.
Our MLJ (2017) write-up on scheduling with hybrid MDPs was acknowledged for presentation within the journal track.
Our work on synthesizing ideas with loops while in the existence of sounds will surface during the Intercontinental journal of approximate reasoning.
Our paper on synthesizing ideas with loops inside the presence of probabilistic noise, accepted the journal of approximate reasoning, has also been recognized into the ICAPS journal keep track of. Preprint to the entire paper here.