1 citations · 1 across the 2 of their papers we have counts for
3 papers
stat.ML2019
Robustness Against Outliers For Deep Neural Networks By Gradient Conjugate Priors
Pavel Gurevich, Hannes Stuke
We analyze a new robust method for the reconstruction of probability distributions of observed data in the presence of output outliers. It is based on a so-called gradient conjugat…
math.DS2018★ 1 cited
Complex time blow-up of the nonlinear heat equation
Hannes Stuke
This paper investigates the connection between blow-up solutions of scalar reaction-diffusion equations, in particular of and its counterpart - eternally exi…
math.ST2018
Gradient conjugate priors and multi-layer neural networks
Pavel Gurevich, Hannes Stuke
The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for…