Many of the current problems with AI systems arise due to the lack of social & ethical intelligence. How could - and how should we - develop moral reasoning in artificial agents? Our answer is in our latest preprint: arxiv.org/abs/2312.01818 - w/ Mirco Musolesi & Steve Hailes 1/7

🚨New paper 🚨 What does it mean to create rational machines? We survey the role of rationality and irrationality within artificial intelligence, and discuss research challenges and open questions in this area. Co-author: Mirco Musolesi arxiv.org/abs/2311.17165

My new pre-print with Stephen Hailes and Mirco Musolesi on information-theoretic state variable selection for reinforcement learning is now out: arxiv.org/pdf/2401.11512…

Delighted to share my new pre-print with Mirco Musolesi & Stephen Hailes. We've developed a new framework for selecting features and interpreting their interactions, with particularly exciting use cases in genetics and neuroscience. Explore our findings: arxiv.org/abs/2405.19212

Pleased to announce that Partial Information Decomposition for Data Interpretability and Feature Selection will appear in AiStats'25. Please give the latest version a read at: arxiv.org/abs/2405.19212. Mirco Musolesi

If you're at AISTATS Conference, join me at Spot 151 in Session 2 (Sun, May 4) to discuss my work with Mirco Musolesi & Stephen Hailes: Partial Information Decomposition for Interpretability. Paper: arxiv.org/abs/2405.19212

New pre-print: arxiv.org/abs/2509.26327. The information bottleneck offers useful but imperfect insights into deep learning. Mirco Musolesi, Steve Hailes, and I introduce a Generalized IB that fills the gaps left by the classic approach.