Erik Englesson

I am PhD student at the division of Robotics, Perception and Learning at KTH, supervised by Hossein Azizpour. My current research interests are related to uncertainty estimation for deep neural networks and transfer learning. Currently, I am looking at estimating uncertainty in data set labels.

This work is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP-AI/MLX) funded by the Knut and Alice Wallenberg Foundation.

Recent publications:

• E. Englesson and H. Azizpour, "Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation," in International Conference on Machine Learning (ICML) Workshops, 2019 Workshop on Uncertainty and Robustness in Deep Learning, 2019.