Artificial Intelligence Research Group Talks

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" and "cows"). In this talk, I will first argue that previously proposed bias mitigation methods that aim...

In healthcare, where accurate and reliable decision-making is paramount, interpretability is essential. Traditional Machine Learning (ML) models have provided valuable insights but often lack transparency in their reasoning, limiting their effectiveness. The recent surge in ML techniques across medical fields such as...

This presentation will explore advancements in genomic research, starting with de novo assembly, where Šikić's lab leads with novel applications of long reads technology. Herro, an innovative AI-based error correction model, increases the accuracy of simplex nanopore reads up to two orders of magnitude, starting a new era...

This talk will present an overview of efforts the UK government has been taking on AI over the past year, including the AI Research Resource, the AI Safety Summit, and with a focus on the AI Safety Institute (AISI). AISI is the world’s first state-backed organization focused on advanced AI safety for the public benefit...

Identifying key patterns of tactics implemented by rival teams, and developing effective responses, lies at the heart of modern football. However, doing so algorithmically remains an open research challenge. To address this unmet need, we propose TacticAI, an AI football tactics assistant developed and evaluated in close...

This talk supports the R255 Advanced Topics in Machine Learning course module on Multimodal Learning and provides a bird’s eye view of the rapidly evolving text-audio landscape, with a focus on music as a primary example of audio data. I will first present types of tasks that exist in this space, then discuss data curation...

I will present deep screening, an ultra-high-throughput approach leveraging the Illumina HiSeq platform for massively parallel sequencing, display, and affinity and kinetics screening at the level up to 109 individual RNA, XNA and protein interactions. Deep screening enabled the rapid discovery of 2-O-methyl-RNA aptamers...

Recent years have witnessed a surge of interest in applying ideas and machinery from machine learning to the design of networked systems. I will discuss my recent efforts to incorporate learning in the context of two fundamental computer networking challenges: routing and congestion control. Specifically, I will discuss...

Retrosynthesis planning is a fundamental challenge in chemistry which aims at designing reaction pathways from commercially available starting materials to a target molecule. Each step in multi-step retrosynthesis planning requires accurate prediction of possible precursor molecules given the target molecule and confidence...

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions, wherein users can correct mispredicted concepts and thus improve the model's...