Skip to content

Deep Evidential Regression on Toy Dataset #17

@nilsleh

Description

@nilsleh

Thank you for the interesting paper and publishing your code. In order to get a better understanding of your method, I have created a google colab (in pytorch) with a toy regression problem. I have implemented your methodology as well as the one from a follow up paper by Meinert et al. 2022. However, neither seem to perform very well, as especially the epistemic uncertainty is not behaving as expected (see below). Therefore, I was wondering if you could give me a hint about what I am missing/doing wrong or a possible explanation. Thanks in advance!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions