The Peril of Popular Deep Learning Uncertainty Estimation Methods

1 code implementation • 9 Dec 2021 • Yehao Liu, Matteo Pagliardini, Tatjana Chavdarova, Sebastian U. Stich

Secondly, we show on a 2D toy example that both BNNs and MCDropout do not give high uncertainty estimates on OOD samples.

Can we learn gradients by Hamiltonian Neural Networks?

1 code implementation • 31 Oct 2021 • Aleksandr Timofeev, Andrei Afonin, Yehao Liu

In this work, we propose a meta-learner based on ODE neural networks that learns gradients.

Inductive Bias