Motivation<\/strong><\/p>\nTrustworthiness, reliability, and robustness in Machine Learning (ML) models become pivotal things to avoid consequential failure when deployed in real life.<\/p>\n
Tools<\/strong><\/p>\nUncertainty estimation and explainable ML can play a significant role in providing intact outcomes. Let\u2019s define both:<\/p>\n
\n- \n
\n- Explainability<\/strong> can provide us with interpretations but in a more human-friendly readable form which reduces the un-easiness of dealing with highly technical concepts for those who are from different backgrounds regarding the model\u2019s predictions.<\/li>\n
- Uncertainty quantification<\/strong> is dealing with the wide spectrum of outcomes we would get due to uncertainties already inherited at both data and model (Aleatroic(data)- Epistemic(model) uncertainties).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n
Work Program<\/strong><\/p>\nWP1: Uncertainty Quantification
\nWP2: Uncertainty Calibration
\nWP3 & WP4: Decomposition of uncertainty sources<\/p>\n
Themes\u2019 relation<\/strong><\/p>\nIP5 contributes and is linked heavily to the other themes of the AID4Crops, it will provide estimates for uncertainty in Theme 1 which would lead to better models and data. Furthermore, for tactical decisions, it would provide outcomes accompanied by uncertainty to guide the policymaker.<\/p>\n
![\"\"](\"http:\/\/aid4crops.uni-bonn.de\/wp-content\/uploads\/2023\/04\/Screenshot-3-300x98.png\")
<\/p>\n","protected":false},"excerpt":{"rendered":"
IP5: Uncertainty meets Explainability: Combining Uncertainty Quantification and Explainable Machine Learning for Crop Monitoring Lead: Ribana Roscher PhD student:\u00a0Mohamed Farag Central Question: How to enhance the understanding of DNN models, and improve the robustness of sensing by combining Explainability and Uncertainty Quantification? Motivation Trustworthiness, reliability, and robustness in Machine Learning (ML) models become pivotal things … <\/p>\n
Continue reading “Uncertainty meets Explainability”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":17,"menu_order":2,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-123","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/pages\/123","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=123"}],"version-history":[{"count":13,"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/pages\/123\/revisions"}],"predecessor-version":[{"id":418,"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/pages\/123\/revisions\/418"}],"up":[{"embeddable":true,"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=\/wp\/v2\/pages\/17"}],"wp:attachment":[{"href":"https:\/\/aid4crops.uni-bonn.de:25000\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"\"](\"http:\/\/aid4crops.uni-bonn.de\/wp-content\/uploads\/2023\/04\/Screenshot-2-300x144.png\")
<\/p>\n