I gave a talk on the workshop on how the synthesis of logic and machine Understanding, Particularly areas such as statistical relational Mastering, can allow interpretability.
Weighted design counting usually assumes that weights are only specified on literals, usually necessitating the need to introduce auxillary variables. We think about a brand new strategy dependant on psuedo-Boolean features, resulting in a far more basic definition. Empirically, we also get SOTA final results.
The paper tackles unsupervised application induction about mixed discrete-continual knowledge, and is approved at ILP.
The paper discusses the epistemic formalisation of generalised arranging in the existence of noisy acting and sensing.
We look at the dilemma of how generalized designs (designs with loops) can be considered suitable in unbounded and continual domains.
A consortia undertaking on trustworthy devices and goverance was accepted late past yr. Information link in this article.
The get the job done is motivated by the need to take a look at and evaluate inference algorithms. A combinatorial argument to the correctness of your Suggestions can https://vaishakbelle.com/ be considered. Preprint right here.
Bjorn and I are promotion a 2 year postdoc on integrating causality, reasoning and awareness graphs for misinformation detection. See below.
We study setting up in relational Markov choice procedures involving discrete and continual states and actions, and an mysterious number of objects (through probabilistic programming).
Together with colleagues from Edinburgh and Herriot Watt, We've place out the demand a different research agenda.
Paulius' Focus on algorithmic tactics for randomly making logic systems and probabilistic logic systems has actually been approved for the ideas and practise of constraint programming (CP2020).
The framework is applicable to a significant class of formalisms, together with probabilistic relational types. The paper also studies the synthesis dilemma in that context. Preprint here.
I gave an invited tutorial the Bath CDT Art-AI. I lined latest traits and long term developments on explainable machine Finding out.
Conference link Our Focus on symbolically interpreting variational autoencoders, as well as a new learnability for SMT (satisfiability modulo theory) formulation acquired acknowledged at ECAI.