Fingerprint
Dive into the research topics where Teresa Dorszewski is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
From Colors to Classes: Emergence of Concepts in Vision Transformers
Dorszewski, T., Tětková, L., Jenssen, R., Hansen, L. K. & Wickstrøm, K. K., 2026, Explainable Artificial Intelligence. Springer, p. 28-47 (Communications in Computer and Information Science, Vol. 2576).Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review
Open AccessFile38 Downloads (Orbit) -
Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
Dorszewski, T., Tětková, L., Linhardt, L. & Hansen, L. K., 2025, Proceedings of the 6th Northern Lights Deep Learning Conference. ML Research Press, p. 41-50 (Proceedings of Machine Learning Research, Vol. 265).Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review
Open AccessFile107 Downloads (Orbit) -
How Redundant Is the Transformer Stack in Speech Representation Models?
Dorszewski, T., Jacobsen, A. K., Tětková, L. & Hansen, L. K., 2025, Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 5 p.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
-
On convex decision regions in deep network representations
Tětková, L., Brüsch, T., Dorszewski, T., Mager, F. M., Aagaard, R. Ø., Foldager, J., Alstrøm, T. S. & Hansen, L. K., 2025, In: Nature Communications. 16, 12 p., 5419.Research output: Contribution to journal › Journal article › Research › peer-review
Open AccessFile57 Downloads (Orbit) -
Convexity Based Pruning of Speech Representation Models
Dorszewski, T., Tetkova, L. & Hansen, L. K., 2024, Proceedings of the 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 6 p. ( IEEE International Workshop on Machine Learning for Signal Processing).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Open Access
Projects
- 1 Active
-
Next generation machine learning explainability
Dorszewski, T. (PhD Student), Hansen, L. K. (Main Supervisor) & Wickstrøm, K. (Supervisor)
01/04/2023 → 20/10/2026
Project: PhD