An AI assistant for football tactics
An AI assistant for football tactics
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 collaboration with domain experts from Liverpool FC. We focus on analysing corner kicks, as they offer coaches the most direct opportunities for interventions and improvements. TacticAI incorporates both a predictive and a generative component, allowing the coaches to effectively sample and explore alternative player setups for each corner kick routine and to select those with the highest predicted likelihood of success. We validate TacticAI on a number of relevant benchmark tasks: predicting receivers and shot attempts and recommending player position adjustments. The utility of TacticAI is validated by aqualitative study conducted with football domain experts at Liverpool FC. We show that TacticAI’s model suggestions are not only indistinguishable from realtactics, but also favoured over existing tactics 90% of the time, and that TacticAI offers an effective corner kick retrieval system. TacticAI achieves these results despite the limited availability of gold-standard data, achieving data efficiency through geometric deep learning.
Speaker
Dr Petar Velickovic (Trinity 2012)
![Petar Velickovic](https://www.alumni.cam.ac.uk/sites/www.alumni.cam.ac.uk/files/styles/150px_wide/public/images/portraits/150px_petar_velickovic.jpg?itok=Bz8ZxPIz)
Dr. Petar Veličković is a Staff Research Scientist at DeepMind, an Associate of Clare Hall, and an Affiliated Lecturer at the University of Cambridge. He earned his PhD in Computer Science from the University of Cambridge (Trinity College) under the supervision of Professor Pietro Liò, a Fellow of Clare Hall.
Dr. Veličković specialises in geometric deep learning, developing neural network architectures that respect the invariances and symmetries in data. Recognised as an ELLIS Scholar in the Geometric Deep Learning Programme, his work focuses on graph representation learning and its applications in algorithmic reasoning and computational biology. He is the first author of Graph Attention Networks, a popular convolutional layer for graphs, and Deep Graph Infomax, a widely-used self-supervised learning pipeline for graphs.
His research has significantly improved travel-time predictions in Google Maps and has guided mathematicians towards new top-tier theorems and conjectures. Dr. Veličković’s contributions have been featured in prominent outlets like Nature, Science, Quanta Magazine, New Scientist, The Independent, Sky News, The Sunday Times, and The Conversation.
Booking information
This event has sold out.
Location
Contact