106 citations · 127 across the 10 of their papers we have counts for
7 papers · 1 filter
Concept-based explainability for an EEG transformer model
Anders Gjølbye, William Lehn-Schiøler, Áshildur Jónsdóttir +2
Deep learning models are complex due to their size, structure, and inherent randomness in training procedures. Additional complexity arises from the selection of datasets and induc…
Generalization by design: Shortcuts to Generalization in Deep Learning
Petr Taborsky, Lars Kai Hansen
We take a geometrical viewpoint and present a unifying view on supervised deep learning with the Bregman divergence loss function - this entails frequent classification and predict…
A simple defense against adversarial attacks on heatmap explanations
Laura Rieger, Lars Kai Hansen
With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification…
Client Adaptation improves Federated Learning with Simulated Non-IID Clients
Laura Rieger, Rasmus M. Th. Høegh, Lars K. Hansen
We present a federated learning approach for learning a client adaptable, robust model when data is non-identically and non-independently distributed (non-IID) across clients. By s…
Probabilistic Decoupling of Labels in Classification
Jeppe Nørregaard, Lars Kai Hansen
In this paper we develop a principled, probabilistic, unified approach to non-standard classification tasks, such as semi-supervised, positive-unlabelled, multi-positive-unlabelled…
Probabilistic Decoupling of Labels in Classification
Jeppe Nørregaard, Lars Kai Hansen
We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implem…