Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

Tunnel effect in CNNS: image reconstruction from max switch locations

Published in IEEE Signal Processing Letters, 2016

Use Google Scholar for full citation

Recommended citation: Matthieu Saint, Laura Rieger, Morten Hannemose, Junmo Kim, "Tunnel effect in CNNS: image reconstruction from max switch locations." IEEE Signal Processing Letters, 2016.

Separable explanations of neural network decisions

Published in Explainable and Interpretable Models in Computer Vision and Machine Learning, 2017

Access paper here

Recommended citation: Laura Rieger, "Separable explanations of neural network decisions." Explainable and Interpretable Models in Computer Vision and Machine Learning, 2017. https://orbit.dtu.dk/en/publications/id(1a8c2782-79cc-418b-97ff-ae97cec0b6e9).html

Tunnel Effect in CNNs: Image Reconstruction from Max Switch Locations

Published in IEEE Signal Processing Letters, 2017

Use Google Scholar for full citation

Recommended citation: M. {De La Roche Saint Andre}, L. Rieger, M. Hannemose, J. Kim, "Tunnel Effect in CNNs: Image Reconstruction from Max Switch Locations." IEEE Signal Processing Letters, 2017.

Structuring Neural Networks for More Explainable Predictions

Published in In the proceedings of Explainable and Interpretable Models in Computer Vision and Machine Learning, 2018

Access paper here Access non-final version here

Recommended citation: Laura Rieger, Pattarawat Chormai, Gr{\'{e}}goire Montavon, Lars Hansen, Klaus-Robert M{\"{u}}ller, "Structuring Neural Networks for More Explainable Predictions." In the proceedings of Explainable and Interpretable Models in Computer Vision and Machine Learning, 2018. http://link.springer.com/10.1007/978-3-319-98131-4{\_}5

Aggregating explanation methods for stable and robust explainability

Published in arXiv preprint arXiv:1903.00519, 2019

Use Google Scholar for full citation

Recommended citation: Laura Rieger, Lars Hansen, "Aggregating explanation methods for stable and robust explainability." arXiv preprint arXiv:1903.00519, 2019.

Interpretability in Intelligent Systems A New Concept?

Published in In the proceedings of Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 2019

Access paper here Access non-final version here

Recommended citation: Lars Hansen, Laura Rieger, "Interpretability in Intelligent Systems A New Concept?." In the proceedings of Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 2019. http://link.springer.com/10.1007/978-3-030-28954-6{\_}3

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge

Published in arXiv preprint arXiv:1909.13584, 2019

Use Google Scholar for full citation

Recommended citation: Laura Rieger, Chandan Singh, W Murdoch, Bin Yu, "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge." arXiv preprint arXiv:1909.13584, 2019.

Aggregating explanation methods for stable and robust explainability

Published in arxiv, 2019

Access paper here

Recommended citation: Laura Rieger, Lars Hansen, "Aggregating explainability methods for neural networks stabilizes explanations." arxiv, 2019. http://arxiv.org/abs/1903.00519

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge

Published in Preprint, 2019

Access paper here

Recommended citation: Laura Rieger, Chandan Singh, W. Murdoch, Bin Yu, "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge." arxiv, 2019. http://arxiv.org/abs/1909.13584