Search Results for author: Cosmas Heiß

Found 5 papers, 1 papers with code

Multilevel CNNs for Parametric PDEs

no code implementations1 Apr 2023 Cosmas Heiß, Ingo Gühring, Martin Eigel

We combine concepts from multilevel solvers for partial differential equations (PDEs) with neural network based deep learning and propose a new methodology for the efficient numerical solution of high-dimensional parametric PDEs.

A neural multilevel method for high-dimensional parametric PDEs

no code implementations NeurIPS Workshop DLDE 2021 Cosmas Heiß, Ingo Gühring, Martin Eigel

In scientific machine learning, neural networks recently have become a popular tool for learning the solutions of differential equations.

Vocal Bursts Intensity Prediction

Self-Supervised Equivariant Scene Synthesis from Video

no code implementations1 Feb 2021 Cinjon Resnick, Or Litany, Cosmas Heiß, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.

In-Distribution Interpretability for Challenging Modalities

no code implementations1 Jul 2020 Cosmas Heiß, Ron Levie, Cinjon Resnick, Gitta Kutyniok, Joan Bruna

It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches.

Physical Simulations

Interval Neural Networks: Uncertainty Scores

1 code implementation25 Mar 2020 Luis Oala, Cosmas Heiß, Jan Macdonald, Maximilian März, Wojciech Samek, Gitta Kutyniok

We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) using a data-driven interval propagating network.

Image Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.