-
on stochastic Riemannian optimization algorithms, these methods still suffer from limitations in computational complexity. The post-doctoral fellow will build upon this preliminary work to investigate
-
analyzed. The tensor model structure estimated by suitable optimization algorithms, such as that recently developed in [GOU20], will be considered as a starting point. • Exploiting data multimodality and
-
of patients treated with immune-checkpoints inhibitors. Our final clinical goals are to help to generate new data-driven tumor response criteria, specifically adapted to immunotherapy, so as to optimize
-
-driven tumor response criteria, specifically adapted to immunotherapy, so as to optimize the current therapeutic strategy. Specific atypical time-varying patterns such as pseudo-progression and dissociated
-
], which states that random neural networks can be pruned to approximate a large class of functions without changing the initial weights. We are also interested in Neural Combinatorial Optimization, where we
-
countries, they are one of the leading causes of mortality and represent a significant societal cost. Preventing these events from the initial stage of care and optimizing safety in the OR have therefore
-
research programme and infrastructure for AI-driven analysis of biomedical data, focusing on precision medicine applications in disease prediction, diagnosis and treatment optimization Promoting and driving
-
research will aim at better exploiting the hand-craft morphological patterns, by means of recent advances in Optimal Transport, in terms of mixed Procrustes-Wasserstein distances [Alvarez-Melis et al., 2019
-
. Unlearning is crucial for biological organisms to adapt and remain flexible in dynamic environments, as well as for machines to optimize output integrity by shedding outdated or harmful associations. In