Johann Ioannou-Nikolaides
Introduction
My research:
Data-driven approaches in particle physics to extract (un)conventional insights, uncover hidden patterns and fundamental physics
My expertise is:
Neutrino Physics (beyond the SM)
A problem I’m grappling with:
Discovering astrophysical neutrino sources using transformer-based architectures
I’ve got my eyes on:
Leveraging latent space representations to uncover hidden structures in particle physics datasets
I want to know more about:
Understanding uncertainties in training datasets and outputting credible confidence intervals
Projects
General searches with (GNN) AutoEncoders
Develop general Graph Neural Network (GNN) reconstruction algorithm(s) for all event types in experiment; based on this GNN architecture, use Variable AutoEncoder (VAE) to encode the dataset in a latent space (LS); apply the VAE to simulated data, also including theoretically motivated but unobserved physics signatures.
