Marina Marie-Claire Höhne (née Vidovic)
Marina Marie-Claire Höhne (née Vidovic)
Leader of a junior research group on explainable AI at TU Berlin, Associate Professor at UiT
Geverifieerd e-mailadres voor tu-berlin.de
Geciteerd door
Geciteerd door
Improving the robustness of myoelectric pattern recognition for upper limb prostheses by covariate shift adaptation
MMC Vidovic, HJ Hwang, S Amsüss, JM Hahne, D Farina, KR Müller
IEEE Transactions on Neural Systems and Rehabilitation Engineering 24 (9 …, 2015
Feature importance measure for non-linear learning algorithms
MMC Vidovic, N Görnitz, KR Müller, M Kloft
arXiv preprint arXiv:1611.07567, 2016
Using transfer learning from prior reference knowledge to improve the clustering of single-cell RNA-Seq data
B Mieth, JRF Hockley, N Görnitz, MMC Vidovic, KR Müller, A Gutteridge, ...
Scientific reports 9 (1), 1-14, 2019
How Much Can I Trust You?--Quantifying Uncertainties in Explaining Neural Networks
K Bykov, MMC Höhne, KR Müller, S Nakajima, M Kloft
arXiv preprint arXiv:2006.09000, 2020
Opening the black box: Revealing interpretable sequence motifs in kernel-based learning algorithms
MMC Vidovic, N Görnitz, KR Müller, G Rätsch, M Kloft
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2015
Covariate shift adaptation in EMG pattern recognition for prosthetic device control
MMC Vidovic, LP Paredes, HJ Hwang, S Amsu, J Pahl, JM Hahne, ...
2014 36th annual international conference of the IEEE engineering in …, 2014
SVM2Motif—reconstructing overlapping DNA sequence motifs by mimicking an SVM predictor
MMC Vidovic, N Görnitz, KR Müller, G Rätsch, M Kloft
PloS one 10 (12), e0144782, 2015
DeepCOMBI: explainable artificial intelligence for the analysis and discovery in genome-wide association studies
B Mieth, A Rozier, JA Rodriguez, MMC Höhne, N Görnitz, KR Müller
NAR genomics and bioinformatics 3 (3), lqab065, 2021
Quantus: an explainable AI toolkit for responsible evaluation of neural network explanations
A Hedström, L Weber, D Bareeva, F Motzkus, W Samek, S Lapuschkin, ...
arXiv preprint arXiv:2202.06861, 2022
Explaining bayesian neural networks
K Bykov, MMC Höhne, A Creosteanu, KR Müller, F Klauschen, ...
arXiv preprint arXiv:2108.10346, 2021
ML2Motif—Reliable extraction of discriminative sequence motifs from learning machines
MMC Vidovic, M Kloft, KR Mueller, N Goernitz
PloS one 12 (3), e0174392, 2017
NoiseGrad—Enhancing Explanations by Introducing Stochasticity to Model Weights
K Bykov, A Hedström, S Nakajima, MMC Höhne
Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6132-6140, 2022
This looks more like that: Enhancing self-explaining models by prototypical relevance propagation
S Gautam, MMC Höhne, S Hansen, R Jenssen, M Kampffmeyer
arXiv preprint arXiv:2108.12204, 2021
Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagation
S Gautam, MMC Höhne, S Hansen, R Jenssen, M Kampffmeyer
2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 1-5, 2022
Self-Supervised Learning for 3D Medical Image Analysis using 3D SimCLR and Monte Carlo Dropout
Y Ali, A Taleb, MMC Höhne, C Lippert
arXiv preprint arXiv:2109.14288, 2021
Visualizing the diversity of representations learned by Bayesian neural networks
D Grinwald, K Bykov, S Nakajima, MMC Höhne
arXiv preprint arXiv:2201.10859, 2022
DORA: Exploring outlier representations in Deep Neural Networks
K Bykov, M Deb, D Grinwald, KR Müller, MMC Höhne
arXiv preprint arXiv:2206.04530, 2022
A comparison of explainable AI solutions to a climate change prediction task
PL Bommer, M Kretschmer, D Bareeva, K Aksoy, M Höhne
EGU22, 2022
Nachvollziehbare Künstliche Intelligenz: Methoden, Chancen und Risiken
MMC Höhne
Datenschutz und Datensicherheit-DuD 45 (7), 453-456, 2021
Improving and interpreting machine learning algorithms with applications
MMC Vidovic
PQDT-Global, 2017
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20