A review of the gumbel-max trick and its extensions for discrete stochasticity in machine learning
The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …
its unnormalized (log-) probabilities. Over the past years, the machine learning community …
Comparative analysis of membership inference attacks in federated learning
Given a federated learning model and a record, a membership inference attack can
determine whether this record is part of the model's training dataset. Federated learning is a …
determine whether this record is part of the model's training dataset. Federated learning is a …
Part-and-whole: A novel framework for deformable medical image registration
J Zhang, Z Liu, Y Ma, X Zhao, B Yang - Applied Intelligence, 2023 - Springer
Medical image registration is a vital initial step in medical image analysis that aims to
establish accurate correspondence between image pairs. Various methods have achieved …
establish accurate correspondence between image pairs. Various methods have achieved …
On the global self-attention mechanism for graph convolutional networks
Applying Global Self-attention (GSA) mechanism over features has achieved remarkable
success on Convolutional Neural Networks (CNNs). However, it is not clear if Graph …
success on Convolutional Neural Networks (CNNs). However, it is not clear if Graph …
On the robustness and generalization of deep learning driven full waveform inversion
The data-driven approach has been demonstrated as a promising technique to solve
complicated scientific problems. Full Waveform Inversion (FWI) is commonly epitomized as …
complicated scientific problems. Full Waveform Inversion (FWI) is commonly epitomized as …
Une revue systématique de la littérature autour du biais, de l'équité et de l'explicabilité
Ce travail fournit une analyse d'une bibliographie autour du biais de l'équité et de
l'explicabilité des algorithmes de l'IA entre 2015 et 2022. Par une approche de Traitement …
l'explicabilité des algorithmes de l'IA entre 2015 et 2022. Par une approche de Traitement …