Name: From Graph Neural Networks to Explainable AI: comprehending and trusting Machine Learning algorithms
Start: 2023-09-20T12:00:00+01:00
End: 2023-09-22T16:00:00+01:00
Location: SPINE Liverpool and University of Liverpool

From Graph Neural Networks to Explainable AI: comprehending and trusting Machine Learning algorithms

from Wednesday, 20 September 2023 (12:00) to Friday, 22 September 2023 (16:00)

Monday, 18 September 2023
Tuesday, 19 September 2023
Wednesday, 20 September 2023

12:00

12:00 - 13:00
13:00 Welcome, introduction and useful info - Monica D'Onofrio
Welcome, introduction and useful info
- Monica D'Onofrio
13:00 - 13:10
13:15 Theory
Theory
13:15 - 14:45

14:45 Coffee Break
Coffee Break
14:45 - 15:15
15:15 Tutorial
Tutorial
15:15 - 18:15
Contributions

15:15 Colab primer GNN
16:45
16:45 - 18:00
Contributions

16:45 Constraining the Complex Relationships Between Galaxies and their Dark Matter Haloes with Machine Learning - Ryan Roberts (LJMU)

16:50 Improving Gamma ray image quality from the SIGMA detector - Owain Griffiths (Liverpool)

17:05 Higgs boson pair production at the LHC: (h->bb)+(h->tautau) final states - Carl Gwilliam

17:10 GNN for SUSY searches: the Wh + MET channel - Joseph Carmignani

17:15 Tau Identification and Classification with GNN - how to improve - Robert McNulty
18:00 Evening reception - drinks and nibbles
Evening reception - drinks and nibbles
18:00 - 19:00
Thursday, 21 September 2023

09:00 Theory
Theory
09:00 - 10:30

10:30 Coffee Break
Coffee Break
10:30 - 11:00

11:00 Hands-on tutorial
Hands-on tutorial
11:00 - 12:30

12:30 Lunch
Lunch
12:30 - 13:30

13:30 Part 1 (Particle Physics)
Part 1 (Particle Physics)
13:30 - 15:00

15:00 Coffee Break
Coffee Break
15:00 - 15:30

15:30 Part 2 (Medical and Neuro Science)
Part 2 (Medical and Neuro Science)
15:30 - 17:00

17:00 Snacks
Snacks
17:00 - 17:30
17:30 Keynote talk: Actionable and responsible AI in medicine - Pietro Liò (University of Cambridge)
Keynote talk: Actionable and responsible AI in medicine
- Pietro Liò (University of Cambridge)
17:30 - 18:30
In this talk Professor Lio will present applications of AI in medicine, focusing on how to build a digital patient twin using graph and hypergraph representation learning and considering physiological (cardiovascular), clinical (inflammation) and molecular variables (multi omics and genetics). He will discuss methodologies that help keeping the clinicians in the loop to avoid excessive automatisation using logic and explainer frameworks. Pietro Li\'o Is Professor in Computational Biology in the AI division and internationally leading researcher in Machine Learning and Computational Biology, member of the Cambridge centre of AI and Medicine and The European Laboratory for Machine Learning (Ellis). He holds two PhDs: one in nonlinear dynamics and complex systems and the second in genomic sciences, therefore interfacing complex systems, machine learning and biomedicine. He is currently contributing the scientific community in developing graph representation learning methods and enhancing their interpretability, particularly in the biomedical fields.
19:00 Dinner - Location TBC
Dinner - Location TBC
19:00 - 20:00
Friday, 22 September 2023

09:00 Follow-up flash talks from day-1 (part 1)
Follow-up flash talks from day-1 (part 1)
09:00 - 10:30

10:30 Coffee Break
Coffee Break
10:30 - 11:00

11:00 Follow-up flash talks from day-1 (part 2)
Follow-up flash talks from day-1 (part 2)
11:00 - 12:00

12:00 Conclusive remarks and Close-out
Conclusive remarks and Close-out
12:00 - 12:30

Choose timezone