Thea Brüsch

According to our database, Thea Brüsch authored at least 7 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

FreqRISE: Explaining time series using frequency masking.

Thea Brüsch, Kristoffer Knutsen Wickstrøm, Mikkel N. Schmidt, Tommy Sonne Alstrøm, Robert Jenssen

Proceedings of the Northern Lights Deep Learning Conference, 2025

REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability.

Kristoffer K. Wickstrøm, Thea Brüsch, Michael C. Kampffmeyer, Robert Jenssen

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

FLEXtime: Filterbank learning for explaining time series.

Thea Brüsch, Kristoffer K. Wickstrøm, Mikkel N. Schmidt, Robert Jenssen, Tommy S. Alstrøm

CoRR, 2024

Contrastive random lead coding for channel-agnostic self-supervision of biosignals.

Thea Brüsch, Mikkel N. Schmidt, Tommy S. Alstrøm

CoRR, 2024

Explaining time series models using frequency masking.

Thea Brüsch, Kristoffer K. Wickstrøm, Mikkel N. Schmidt, Tommy S. Alstrøm, Robert Jenssen

CoRR, 2024

2023

On convex conceptual regions in deep network representations.

Lenka Tetková, Thea Brüsch, Teresa Karen Scheidt, Fabian Martin Mager, Rasmus Ørtoft Aagaard, Jonathan Foldager, Tommy Sonne Alstrøm, Lars Kai Hansen

CoRR, 2023

Multi-View Self-Supervised Learning For Multivariate Variable-Channel Time Series.

Thea Brüsch, Mikkel N. Schmidt, Tommy S. Alstrøm

Proceedings of the 33rd IEEE International Workshop on Machine Learning for Signal Processing, 2023