Zobrazeno 1 - 10
of 79
pro vyhledávání: '"Perraudin, Nathanael"'
Autor:
Bergmeister, Andreas, Palgunadi, Kadek Hendrawan, Bosisio, Andrea, Ermert, Laura, Koroni, Maria, Perraudin, Nathanaël, Dirmeier, Simon, Meier, Men-Andrin
Accurate prediction and synthesis of seismic waveforms are crucial for seismic hazard assessment and earthquake-resistant infrastructure design. Existing prediction methods, such as Ground Motion Models and physics-based simulations, often fail to ca
Externí odkaz:
http://arxiv.org/abs/2410.19343
Autor:
Teurtrie, Adrien, Perraudin, Nathanaël, Holvoet, Thomas, Chen, Hui, Alexander, Duncan T. L., Obozinski, Guillaume, Hébert, Cécile
We present the development of a new algorithm which combines state-of-the-art energy-dispersive X-ray (EDX) spectroscopy theory and a suitable machine learning formulation for the hyperspectral unmixing of scanning transmission electron microscope ED
Externí odkaz:
http://arxiv.org/abs/2404.17496
We consider the problem of regularized Poisson Non-negative Matrix Factorization (NMF) problem, encompassing various regularization terms such as Lipschitz and relatively smooth functions, alongside linear constraints. This problem holds significant
Externí odkaz:
http://arxiv.org/abs/2404.16505
In the realm of generative models for graphs, extensive research has been conducted. However, most existing methods struggle with large graphs due to the complexity of representing the entire joint distribution across all node pairs and capturing bot
Externí odkaz:
http://arxiv.org/abs/2312.11529
Autor:
Russo, Stefania, Perraudin, Nathanaël, Stalder, Steven, Perez-Cruz, Fernando, Leitao, Joao Paulo, Obozinski, Guillaume, Wegner, Jan Dirk
In this technical report we compare different deep learning models for prediction of water depth rasters at high spatial resolution. Efficient, accurate, and fast methods for water depth prediction are nowadays important as urban floods are increasin
Externí odkaz:
http://arxiv.org/abs/2302.10062
Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks. While these approaches have also been applied to the generation of discrete graphs, they have, so far, relied on continuous Gauss
Externí odkaz:
http://arxiv.org/abs/2210.01549
Autor:
Stalder, Steven, Perraudin, Nathanaël, Achanta, Radhakrishna, Perez-Cruz, Fernando, Volpi, Michele
Publikováno v:
Advances in Neural Information Processing Systems 35 (2022) 84-94
An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, doing this accurately is a difficult task due to the black-box nature o
Externí odkaz:
http://arxiv.org/abs/2205.11266
We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral conditioning allows for direct
Externí odkaz:
http://arxiv.org/abs/2204.01613
Autor:
Rust, Romana, Xydis, Achilleas, Heutschi, Kurt, Perraudin, Nathanaël, Casas, Gonzalo, Du, Chaoyu, Strauss, Jürgen, Eggenschwiler, Kurt, Perez-Cruz, Fernando, Gramazio, Fabio, Kohler, Matthias
Publikováno v:
Building Acoustics. February 2021
In this paper, we present a novel interdisciplinary approach to study the relationship between diffusive surface structures and their acoustic performance. Using computational design, surface structures are iteratively generated and 3D printed at 1:1
Externí odkaz:
http://arxiv.org/abs/2109.12014
Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these
Externí odkaz:
http://arxiv.org/abs/2012.15000