The 120th ICREA Colloquium ‘Trustworthy AI and quantum computing for healthcare’

ABSTRACT

AI has had a profound effect in all walks of life, not least in healthcare. The impressive
performance of these methods is partly due to the development of very efficient
approaches to solve highly overparameterized neural networks. These are “black box”
systems, dificult to interpret and predict, leading to a problem of trustworthiness,
particularly for sentitive domains such as healthcare. ICREA Research Professor Miguel A.
González Ballester (UPF) will first present several works addressing these aspects,
including explainability of neural networks, uncertainty modelling, and hybrid
mechanistic-machine learning models (e.g. ERC Synergy project Zee-Zoom-Zap). We will
then delve into the interface between machine learning and quantum computing, with Dr.
Alba Cervera-Lierta (BSC), exploring early collaborative works on the development of
quantum machine learning approaches for healthcare. First, we will show some results on
the establishment of quantum diffusion models for medical image analysis. Finally, we
will link back to trustworthy AI, formulating a quantum annealing framework for
explainable deep learning.