Photo of Amanda Olmin

Amanda Olmin

PhD student

My research lies in the intersection between the fields of deep learning and probabilistic modelling. The aim is to develop deep learning models that can reason about uncertainties, such as those emerging from noise inherent in most data.

Publications

2024

Amanda Olmin (2024) Perspectives on Predictive and Annotation Uncertainty in Probabilistic Machine Learning
Amanda Olmin, Jakob Lindqvist, Lennart Svensson, Fredrik Lindsten (2024) On the connection between Noise-Contrastive Estimation and Contrastive Divergence INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, p. 3016-3024 (Conference paper)

2023

Jakob Lindqvist, Amanda Olmin, Lennart Svensson, Fredrik Lindsten (2023) Generalised Active Learning With Annotation Quality Selection IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP) (Conference paper) Continue to DOI
Amanda Olmin, Jakob Lindqvist, Lennart Svensson, Fredrik Lindsten (2023) Active Learning with Weak Supervision for Gaussian Processes Neural Information Processing 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part V, p. 195-204 (Conference paper) Continue to DOI

2022

Amanda Olmin, Fredrik Lindsten (2022) Robustness and Reliability When Training With Noisy Labels Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022, p. 922-942 (Conference paper)

Research

Organisation

Colleagues at STIMA