11 citations · 11 across the 2 of their papers we have counts for
2 papers
cs.LG2021★ 11 cited
The Peril of Popular Deep Learning Uncertainty Estimation Methods
Yehao Liu, Matteo Pagliardini, Tatjana Chavdarova +1
Uncertainty estimation (UE) techniques -- such as the Gaussian process (GP), Bayesian neural networks (BNN), Monte Carlo dropout (MCDropout) -- aim to improve the interpretability…
cs.LG2021
Can we learn gradients by Hamiltonian Neural Networks?
Aleksandr Timofeev, Andrei Afonin, Yehao Liu
In this work, we propose a meta-learner based on ODE neural networks that learns gradients. This approach makes the optimizer is more flexible inducing an automatic inductive bias…