The Artificial Intelligence Modelling Lab (AIML) engages in a range of theoretical and applied research in Artificial Intelligence (AI) and Machine Learning (ML). Particular areas of interest include interactive theorem proving, formal modelling and verification, machine learning and its combination with higher level symbolic reasoning, as well as its application to healthcare and other complex domains.

Recent Events

Verified Optimisation in Lean

Date: 22nd October 2021

Convex optimisation is a subfield of mathematics that studies convex functions and their maxima/minima over a given domain, with applications in control synthesis, signal processing and operations research to mention a few. We describe the how the Lean theorem prover might be used to rigorously check algorithms in the domain, with neural network verification as a potential case study.
Speaker: Ramon Mir Fernandez

In this work, a Relational Graph Attention Network is extended to operate on multimodal biological input and is compared alongside previously established side effect prediction methods to evaluate the efficacy of deep Network Representation Learning for adverse drug reaction prediction.
Speaker: Lauren DeLong

Mechanising Process Composition

Date: 10th September 2021

I will give a brief overview of processes and resources, as well as their formalisation in Isabelle/HOL and demonstrate some of its features such as located resources and sensing actions. I will relate our process compositions to proofs in linear logic. Finally I will sum up our future research plans.
Speaker: Filip Smola