AIML 3-minute thesis competition (Practice Round, Batch 2)

Date: 7th December 2021

Time: 14:00-16:00

In this preliminary round of the AI Modelling Lab’s 3-minute thesis/project competition, a second batch of speakers will give us an exciting overview of their research with the help of a single slide. The topics range from healthcare/medicine to the formal foundations of physics, covering both knowledge/symbolic- and data-driven AI.
Speakers: Filip Smola, Rui Zhao, James Vaughan, Lauren DeLong, Jake Palmer, Mark Chevallier, Richard Schmoetten, Petros Papapanagiotou

Continue Reading →

AIML 3-minute thesis competition (Practice Round, Batch 1)

Date: 19th November 2021

Time: 14:00-16:00

In this preliminary round of the AI Modelling Lab's 3-minute thesis/project competition, a first batch of speakers will give us an exciting overview of their research with the help of a single slide. The topics range from healthcare to formalised mathematics, covering both knowledge/symbolic- and data-driven AI.
Speakers: Imogen Morris, Adarsh Prabhakaran,Jorge Gaete-Villegas, Jiawei Zheng, Zonglin Ji, Ramon Mir Fernández

Continue Reading →

Verified Optimisation in Lean

Date: 22nd October 2021

Time: 14:00-16:00

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

Continue Reading →

A Formalisation of Markov Decision Processes

Date: 27th August 2021

Time: 10:30-12:00

I will talk about a formalised model of Markov Decision Processes with rewards. I'll discuss formal proofs of value convergence and of the existence of an optimal policy by vector representation of functions on the states.
Speaker: Mark Chevallier

Continue Reading →

Tree Search using Human Expert’s Knowledge

Date: 16th July 2021

Time: 15:15-16:00

Tree search algorithms are used to solve challenging problems like planning problems and combinatorial optimization search. In this presentation, we shall explore how we can integrate human experience directly in tree search without encoding them into objective functions. This approach aims to address the issues of information loss that lead to degraded solution quality and result in increased computational costs.
Spealer: Mustafa Faisal Abdelwahed

Continue Reading →