A Systematic Review on Model-agnostic XAI Libraries
Description
During the last few years the topic explainable artificial intelligence (XAI) has become a hotspot in the ML research community. Model-agnostic interpretation methods propose separating the explanations from the ML model, making these explanation methods reusable through XAI libraries. In this paper we have reviewed some selected XAI libraries and provide examples of different model agnostic explanations for the same black box model with the same training data. The context of the research conducted in this paper is the iSee project 1 that will show how users of Artificial Intelligence (AI) can capture, share and re-use their experiences of AI explanations with other users who have similar explanation needs.
Notes
Files
XCBR___XAI_libraries.pdf
Files
(1.2 MB)
Name | Size | Download all |
---|---|---|
md5:17465aede7524e9ce4663a74e9cac616
|
1.2 MB | Preview Download |