Information Theory for Distributed AI

Laying the theoretical foundations of learning and intelligence across distributed agents with heterogenous computational capabilities, diverse and private datasets, and limited communication links
What we doResearch themes

EPSRC Funded AI Research Hub

INFORMED-AI is one of three EPSRC funded hubs on the mathematical foundations of artificial intelligence. A joint venture between the universities of Bristol, Cambridge, Durham and Imperial College, London, its focus is on collective intelligence in distributed multi-agent systems such as power grids, transport and communication networks, robot swarms, etc.

The hub seeks to promote research on fundamental information-theoretic aspects of learning and decision-making in collectives as well as on the development of decentralised algorithms that preserve privacy, are robust to malicious agents and resilient to network failures. The hub is part of the recent UKRI investment of £80 million into AI research, and will be instrumental in shaping the mathematical foundations of AI and machine learning for future development.