Institute for Data Science and AI Seminar: Petar Veličković A digital Futures event - 27 october 2023

On the 27th October 2023, the Institute for Data Science and AI Seminar Series welcomed Petar Veličković, Staff Research Scientist at Google Deep Mind and Affiliated Lectureship at the University of Cambridge, to give a presentation titled ‘Decoupling the Input and the Computational Graph: The Most Important Unsolved Problem in Graph Representation.’

Organised in partnership with the Turing Innovation Catalyst and ID Manchester, this seminar was part of the Official AI Fringe, a series of events hosted across the UK to complement the UK Government’s AI Safety Summit.

Attendees networking prior to the seminar

Held at Bruntwood SciTech’s No. 1 Circle Square, a diverse array of attendees travelled across the UK and the globe to learn about Petar's ground-breaking research in Data Science and AI. Ranging across academia and industry, the Institute for Data Science and Artificial Intelligence (IDSAI) hosted interdisciplinary researchers from world-leading universities, as well as renowned professionals from HMRC and Ofcom.

Attendees at the start of the seminar

Dr Julia Handl, Professor in Decision Sciences in Alliance Manchester Business School at The University of Manchester, kicked off proceedings with a short welcome and introduction to all attendees. Following this, Petar commenced his talk on Graph Neural Networks and Geometric Deep Learning.

Dr Julia Handl introducing the event

Petar showcased his research expertise in devising neural network architectures that operate on nontrivially structured data, and their applications in algorithmic researching and computational biology. Introducing the audience to a vibrant area of graph rewiring, Petar dispelled the assumption that the input graph is the ground-truth.

Veličković giving his presentation

The presentation catalysed a lively discussion in the following Q&A session. The interdisciplinary talk had attracted attendees from backgrounds ranging from Neuroscience to Law who were interested in innovative AI applications.

Q&A Session

To bridge interdisciplinary connections across industry and academia, a networking session took place. Many attendees stayed back for the opportunity to discuss insights with Petar.

Attendees discussing ideas with Veličković.

If you missed this event, you can watch it back here:

If you are interested in joining future events you can sign up for our IDSAI newsletter and follow our Twitter account @idsai_uom. Delivered by The University of Manchester's wider Digital Futures network, the Institute for Data Science and Artificial Intelligence is highly interdisciplinary and delivers the University's Data Science strategy - connect with us and keep in touch: