Model-Agnostic Visual Explanation of Machine Learning Models Based on Heat Map

Simple item page
dc.contributor.authorSawada, Shokoen_US
dc.contributor.authorToyoda, Masashien_US
dc.contributor.editorMadeiras Pereira, João and Raidou, Renata Georgiaen_US
dc.date.accessioned2019-06-02T18:21:14Z
dc.date.available2019-06-02T18:21:14Z
dc.date.issued2019
dc.description.abstractIt is essential to assess the trustworthiness of the machine learning models when deploying them to real-world applications, such as healthcare and risk management, in which domain experts need to make critical decisions. We propose a visual analysis method for supporting domain experts to understand and improve a given machine learning model based on a model-agnostic interpretable explanation technique. Our visualization method provides a heat map matrix as an overview of the model explanation and helps efficient feature engineering and data cleaning. We demonstrate our visualization method on a text classification task.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEuroVis 2019 - Posters
dc.identifier.doi10.2312/eurp.20191140
dc.identifier.isbn978-3-03868-088-8
dc.identifier.pages37-39
dc.identifier.urihttps://doi.org/10.2312/eurp.20191140
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/eurp20191140
dc.publisherThe Eurographics Associationen_US
dc.subjectHuman
dc.subjectcentered computing
dc.subjectHeat maps
dc.subjectVisual analytics
dc.subjectComputing methodologies
dc.subjectMachine learning
dc.titleModel-Agnostic Visual Explanation of Machine Learning Models Based on Heat Mapen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
037-039.pdf
Size:
341.33 KB
Format:
Adobe Portable Document Format
Download
Collections
EuroVisPosters2019