Thèse de doctorat : Università della Svizzera italiana, 2022 ; 2022INF001.
Dynamical systems have been used to describe a vast range of phenomena, including physical sciences, biology, neurosciences, and economics just to name a few. The development of a mathematical theory for dynamical systems allowed researchers to create precise models of many phenomena, predicting their behaviors with great accuracy. For many challenges of dynamical systems, highly accurate...
|
Thèse de doctorat : Università della Svizzera italiana, 2021 ; 2021INFO014.
This thesis explores the field of graph neural networks, a class of deep learning models designed to learn representations of graphs. We organise the work into two parts. In the first part, we focus on the essential building blocks of graph neural networks. We present three novel operators for learning graph representations: one graph convolutional layer and two methods for pooling. We put...
|
In: Entropy, 2021, vol. 23, no. 1, p. 27 p
Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to very restricted model classes, where exact or approximate probabilistic inference is feasible. However, developments in variational inference, a general form of approximate probabilistic inference that originated in statistical...
|
In: Bioinformatics, 2018, vol. 34, no. 17, p. i647-i655
|
In: Networks and Spatial Economics, 2015, vol. 15, no. 1, p. 117-147
|
In: Molecular Genetics and Genomics, 2015, vol. 290, no. 4, p. 1247-1263
|
In: Bioinformatics, 2018, vol. 34, no. 2, p. 258-266
|
Thèse de doctorat : Université de Fribourg, 2021.
|
Mémoire de master : Université de Fribourg, 2020.
|
Thèse de doctorat : Università della Svizzera italiana, 2020 ; 2020INFO020.
Stochastic Optimization Problems take uncertainty into account. For this reason they are in general more realistic than deterministic ones, meanwhile, more difficult to solve. The challenge is both on modelling and computation aspects: exact methods usually work only for small instances, besides, there are several problems with no closed-form expression or hard- to-compute objective functions....
|