Bernhard Mehlig

According to our database, Bernhard Mehlig authored at least 9 papers between 2019 and 2023.

Collaborative distances:

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

2023

Looking at the posterior: accuracy and uncertainty of neural-network predictions.

Hampus Linander, Oleksandr Balabanov, Henry Yang, Bernhard Mehlig

Mach. Learn. Sci. Technol., December, 2023

Finite-time Lyapunov exponents of deep neural networks.

L. Storm, Hampus Linander, J. Bec, Kristian Gustavsson, Bernhard Mehlig

CoRR, 2023

Bayesian Posterior Approximation With Stochastic Ensembles.

Oleksandr Balabanov, Bernhard Mehlig, Hampus Linander

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Constraints on parameter choices for successful time-series prediction with echo-state networks.

L. Storm, Kristian Gustavsson, Bernhard Mehlig

Mach. Learn. Sci. Technol., December, 2022

Looking at the posterior: on the origin of uncertainty in neural-network classification.

Hampus Linander, Oleksandr Balabanov, Henry Yang, Bernhard Mehlig

CoRR, 2022

Constraints on parameter choices for successful reservoir computing.

L. Storm, Kristian Gustavsson, Bernhard Mehlig

CoRR, 2022

Improving Traffic Sign Recognition by Active Search.

Sami Jaghouar, Hannes Gustafsson, Bernhard Mehlig, Erik Werner, Niklas Gustafsson

Proceedings of the Pattern Recognition, 2022

2020

Machine learning for active matter.

Frank Cichos, Kristian Gustavsson, Bernhard Mehlig, Giovanni Volpe

Nat. Mach. Intell., 2020

2019

Artificial Neural Networks.

Bernhard Mehlig

CoRR, 2019