-
Topological Graph Neural Networks
Graph neural networks (GNNs) are a powerful architecture for tackling gr...
02/15/2021 ∙ by Max Horn, et al. ∙
67
∙
share
read it
-
Translational Equivariance in Kernelizable Attention
While Transformer architectures have show remarkable success, they are b...
02/15/2021 ∙ by Max Horn, et al. ∙
0
∙
share
read it
-
Path Imputation Strategies for Signature Models
The signature transform is a 'universal nonlinearity' on the space of co...
05/25/2020 ∙ by Michael Moor, et al. ∙
10
∙
share
read it
-
Set Functions for Time Series
Despite the eminent successes of deep neural networks, many architecture...
09/26/2019 ∙ by Max Horn, et al. ∙
0
∙
share
read it
-
Topological Autoencoders
We propose a novel approach for preserving topological structures of the...
06/03/2019 ∙ by Michael Moor, et al. ∙
0
∙
share
read it
-
Machine learning for early prediction of circulatory failure in the intensive care unit
Intensive care clinicians are presented with large quantities of patient...
04/16/2019 ∙ by Stephanie L. Hyland, et al. ∙
0
∙
share
read it
-
Temporal Convolutional Networks and Dynamic Time Warping can Drastically Improve the Early Prediction of Sepsis
Motivation: Sepsis is a life-threatening host response to infection asso...
02/05/2019 ∙ by Michael Moor, et al. ∙
0
∙
share
read it
-
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
While many approaches to make neural networks more fathomable have been ...
12/23/2018 ∙ by Bastian Rieck, et al. ∙
16
∙
share
read it
