Explainable AI Methods - A Brief Overview
Medical University of Graz · BOKU University · +4 more institutions
Abstract
Abstract Explainable Artificial Intelligence (xAI) is an established field with a vibrant community that has developed a variety of very successful approaches to explain and interpret predictions of complex machine learning models such as deep neural networks. In this article, we briefly introduce a few selected methods and discuss them in a short, clear and concise way. The goal of this article is to give beginners, especially application engineers and data scientists, a quick overview of the state of the art in this current topic. The following 17 methods are covered in this chapter: LIME, Anchors, GraphLIME, LRP, DTD, PDA, TCAV, XGNN, SHAP, ASV, Break-Down, Shapley Flow, Textual Explanations of Visual…
Citation impact
- FWCI
- 112.92
- Percentile
- 100%
- References
- 68
Authors
5- AHAndreas HolzingerCorresponding
Medical University of Graz, BOKU University
- ASAnna Saranti
Medical University of Graz, BOKU University
- CMChristoph Molnar
Leibniz Institute for Prevention Research and Epidemiology - BIPS
- PBPrzemysław Biecek
Warsaw University of Technology, University of Warsaw
- WSWojciech Samek
Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute
Topics & keywords
- Computer science
- Variety (cybernetics)
- Field (mathematics)
- Artificial intelligence
- Artificial neural network
- Data science
- Machine learning