Multicriteria interpretability driven deep learning
M Repetto - Annals of Operations Research, 2022 - Springer
Deep Learning methods are well-known for their abilities, but their interpretability keeps
them out of high-stakes situations. This difficulty is addressed by recent model-agnostic …
them out of high-stakes situations. This difficulty is addressed by recent model-agnostic …
[HTML][HTML] Closed-loop optimisation of neural networks for the design of feedback policies under uncertainty
Solving model predictive control (MPC) problems online can be computationally intractable,
especially when considering uncertainty and nonlinear systems. One approach to avoid this …
especially when considering uncertainty and nonlinear systems. One approach to avoid this …
A systematic approach to find the hyperparameters of artificial neural networks applied to damage detection in composite materials
Abstract Artificial Neural Networks applied to Structural Health Monitoring (SHM) have been
used to detect damage in composite structures. However, tuning the ANN architecture and …
used to detect damage in composite structures. However, tuning the ANN architecture and …
Universal differential equations for glacier ice flow modelling
Geoscientific models are facing increasing challenges to exploit growing datasets coming
from remote sensing. Universal Differential Equations (UDEs), aided by differentiable …
from remote sensing. Universal Differential Equations (UDEs), aided by differentiable …
Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll concentration in the Black Sea
Satellite observations provide a global or near-global coverage of the World Ocean. They
are however affected by clouds (among others), which severely reduce their spatial …
are however affected by clouds (among others), which severely reduce their spatial …
Toward mechanistic models “augmented” by machine learning. Example of a drying simulation data set exploited by a Physics Informed Neural Network
P Perré - Drying Technology, 2024 - Taylor & Francis
Mechanistic modeling of drying is well-established since several decades. Based on
fundamental balance equations and driven by relevant material parameters, it can predict …
fundamental balance equations and driven by relevant material parameters, it can predict …
Control Strategies for Multirotor Wind Turbines
F Matras, M Dinhoff Pedersen - Wind Energy Science …, 2025 - wes.copernicus.org
This work considers steady-state aspects of multirotor windturbine control. In contrast to most
literature on the topic, the underlying multirotor model includes the aerodynamic interactions …
literature on the topic, the underlying multirotor model includes the aerodynamic interactions …
Minimizing oracle-structured composite functions
We consider the problem of minimizing a composite convex function with two different
access methods: an oracle, for which we can evaluate the value and gradient, and a …
access methods: an oracle, for which we can evaluate the value and gradient, and a …