-
on baseline patients’ profile. Finally, we aim at enriching spatio-temporal treatment response models accounting for multiple imaging modalities (PET – CT) along with clinical and biological informations
-
, for example by developing novel approaches to constrain learning-based models by mechanistic priors. Thanks to the proposed theory, we will investigate the use of simulations informed by such mechanistic
-
experimental data and is testable across multiple unlearning scenarios. For this we plan to apply for the first time Spiking Neural Networks (SNNs) to the modeling of unlearning. SNNs have recently shown
-
Virtual laboratory to predict the ability of a fluctuating biomass to satisfy a material use-VARIOUS
modelling and simulation tools familiar with and initiated in biomass and plant fibres, experts in materials science specialised in biomass and natural fibres, and users of digital tools. INRAE's life quality