Explainability in CNN Models By Means of Z-Scores
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 for fusion of Synthetic Aperture Radar (SAR) and Microwave Radiometry (MWR) data, is applied to prediction of arctic se...
| Main Authors: | , , |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
arXiv
2021
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2102.05874 https://arxiv.org/abs/2102.05874 |
| id |
ftdatacite:10.48550/arxiv.2102.05874 |
|---|---|
| record_format |
openpolar |
| spelling |
ftdatacite:10.48550/arxiv.2102.05874 2023-05-15T15:05:08+02:00 Explainability in CNN Models By Means of Z-Scores Malmgren-Hansen, David Nielsen, Allan Aasbjerg Pedersen, Leif Toudal 2021 https://dx.doi.org/10.48550/arxiv.2102.05874 https://arxiv.org/abs/2102.05874 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CC-BY Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2102.05874 2022-03-10T14:52:08Z 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 for fusion of Synthetic Aperture Radar (SAR) and Microwave Radiometry (MWR) data, is applied to prediction of arctic sea ice. With the analysis the importance of MWR relative to SAR is found to favor MWR components. Further, as the model represents image features at different scales, the relative importance of these are as well analyzed. The suggested methodology offers a simple and easy framework for analyzing output layer components and can reduce the number of components for further analysis with e.g. common NN visualization methods. : Intended and accepted for the "Deep Learning Meets Earth Sciences: From Hybrid Modeling to Explainability" workshop at IGARSS 2020, but was redrawn due to authors being unable to participate when lockdown restrictions moved the conference days. The work was conducted 2019 under the Automated Sea Ice Products (ASIP) project funded by the Innovation Fund Denmark Article in Journal/Newspaper Arctic Sea ice DataCite Metadata Store (German National Library of Science and Technology) Arctic |
| institution |
Open Polar |
| collection |
DataCite Metadata Store (German National Library of Science and Technology) |
| op_collection_id |
ftdatacite |
| language |
unknown |
| topic |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
| spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Malmgren-Hansen, David Nielsen, Allan Aasbjerg Pedersen, Leif Toudal Explainability in CNN Models By Means of Z-Scores |
| topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
| description |
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 for fusion of Synthetic Aperture Radar (SAR) and Microwave Radiometry (MWR) data, is applied to prediction of arctic sea ice. With the analysis the importance of MWR relative to SAR is found to favor MWR components. Further, as the model represents image features at different scales, the relative importance of these are as well analyzed. The suggested methodology offers a simple and easy framework for analyzing output layer components and can reduce the number of components for further analysis with e.g. common NN visualization methods. : Intended and accepted for the "Deep Learning Meets Earth Sciences: From Hybrid Modeling to Explainability" workshop at IGARSS 2020, but was redrawn due to authors being unable to participate when lockdown restrictions moved the conference days. The work was conducted 2019 under the Automated Sea Ice Products (ASIP) project funded by the Innovation Fund Denmark |
| format |
Article in Journal/Newspaper |
| author |
Malmgren-Hansen, David Nielsen, Allan Aasbjerg Pedersen, Leif Toudal |
| author_facet |
Malmgren-Hansen, David Nielsen, Allan Aasbjerg Pedersen, Leif Toudal |
| author_sort |
Malmgren-Hansen, David |
| title |
Explainability in CNN Models By Means of Z-Scores |
| title_short |
Explainability in CNN Models By Means of Z-Scores |
| title_full |
Explainability in CNN Models By Means of Z-Scores |
| title_fullStr |
Explainability in CNN Models By Means of Z-Scores |
| title_full_unstemmed |
Explainability in CNN Models By Means of Z-Scores |
| title_sort |
explainability in cnn models by means of z-scores |
| publisher |
arXiv |
| publishDate |
2021 |
| url |
https://dx.doi.org/10.48550/arxiv.2102.05874 https://arxiv.org/abs/2102.05874 |
| geographic |
Arctic |
| geographic_facet |
Arctic |
| genre |
Arctic Sea ice |
| genre_facet |
Arctic Sea ice |
| op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
| op_rightsnorm |
CC-BY |
| op_doi |
https://doi.org/10.48550/arxiv.2102.05874 |
| _version_ |
1766336881792909312 |