Mathematics & Theory
The formal structures that govern learning, generalisation and inference.
Our work in mathematics and theory brings together researchers across applied mathematics, statistics, information theory, optimisation, theoretical computer science and the related formal sciences. The objects of study are the structures that govern how systems learn, represent information, generalise and fail. The emphasis is on clarity, abstraction and limits: not merely how present systems work, but what is in principle possible, what is provably impossible and where present theories begin to break down. Much of the field's present confusion sits, in our view, in the gap between these regions.
- What mathematical principles govern learning, generalisation and inference?
- Where do formal guarantees end and where must empirical investigation begin?
- What roles do information theory, optimisation and dynamical systems play in modern learning?
- How are we to reason rigorously about systems we cannot, in general, inspect in full?
Conferences
Mathematics and theory carry the load at our peer-reviewed conference, the International Conference on the Mathematics of Neuroscience and AI. At the AE Global Summit, the same questions arise wherever a claim about capability meets the formal limits that constrain it.
Spotlight- Dynamical systems principles underlie the ubiquity of biological data manifolds
Spotlight talk by Dr Arthur Pellegrino presents "Dynamical systems principles underlie the ubiquity of biological data manifolds" Abstract -…
Watch →
Spotlight - Algorithmic representations in the human brain that underlie schema generalisation
Spotlight talk by Svenja Küchenhoff presents "Algorithmic representations in the human brain that underlie schema generalisation" Abstract -…
Watch →
Spotlight - An abstract relational map emerges in the human medial prefrontal cortex with time
Spotlight talk by Dr Alon Baram presents "An abstract relational map emerges in the human medial prefrontal cortex with time" Abstract - It…
Watch →
Spotlight - Invariant probabilistic representations in neural networks
Spotlight talk by Ishan Kalburge presents "Invariant probabilistic representations in neural networks" Abstract - While mounting evidence in…
Watch →
Spotlight - Collective Moral Reasoning in Multi-Agent LLMs
Spotlight talk by Dr Anita Keshmirian presents "Collective Moral Reasoning in Multi-Agent LLMs" Abstract - As artificial intelligence system…
Watch →
Spotlight- Uncertainty in latent representations of variational autoencoders for visual tasks
Spotlight talk by Domonkos Martos presents "Uncertainty in latent representations of variational autoencoders optimized for visual tasks" Ab…
Watch →ThAT Ambassador Programme
The Thinking About Thinking Ambassador Programme is an open, application-based pathway for students and early-career researchers who wish to take part in serious, interdisciplinary conversations about intelligence. Ambassadors support our conferences, workshops, and community initiatives; in turn, they help to extend thoughtful dialogue across universities, disciplines and countries. The programme is designed for those who care, in earnest, about ideas, collaboration, and the construction of intellectual community.
Outstanding ambassadors who, over time, demonstrate sustained contribution, leadership and intellectual engagement may, in due course, be invited into the Thinking About Thinking Fellowship, a private, invitation-only programme reserved for long-term contributors to the work.