5 citations · 9 across the 4 of their papers we have counts for
4 papers
Explainability in CNN Models By Means of Z-Scores
David Malmgren-Hansen, Allan Aasbjerg Nielsen, Leif Toudal Pedersen
This paper explores the similarities of output layers in Neural Networks (NNs) with logistic regression to explain importance of inputs by Z-scores. The network analyzed, a network…
Transfer Learning with Convolutional Networks for Atmospheric Parameter Retrieval
David Malmgren-Hansen, Allan Aasbjerg Nielsen, Valero Laparra +1
The Infrared Atmospheric Sounding Interferometer (IASI) on board the MetOp satellite series provides important measurements for Numerical Weather Prediction (NWP). Retrieving accur…
Spatial noise-aware temperature retrieval from infrared sounder data
David Malmgren-Hansen, Valero Laparra, Allan Aasbjerg Nielsen +1
In this paper we present a combined strategy for the retrieval of atmospheric profiles from infrared sounders. The approach considers the spatial information and a noise-dependent…
Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models
David Malmgren-Hansen, Allan Aasbjerg Nielsen, Rasmus Engholm
Convolutional Neural Networks (Convnets) have achieved good results in a range of computer vision tasks the recent years. Though given a lot of attention, visualizing the learned r…