Giacomo De Palma is leader of Task 8.2.2 "Foundations of quantum machine learning in the hard sciences" - WP 8.2 "Founding principles of Machine Learning for controllable and explainable Artificial Intelligence"
Foundations of quantum machine learning in the hard sciences
Quantum neural networks have the potential to provide major advantages with respect to classical neural networks, but there is no problem of practical relevance yet where such advantage has been rigorously proved. This task consists in analyzing the training dynamics of quantum neural networks and the probability distribution of the functions that they generate through the lens of the emerging field of quantum optimal mass transport, and therefore rigorously determining their capabilities to outperform classical neural networks.
https://future-ai-research.it/spoke8/