Workflow for Knowledge Extraction from Neural Network Classifiers

2018 59th International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS 2018) 2018
Andrejs Bondarenko, Ludmila Aleksejeva

Artificial neural network classifiers are widespread models used by many machine learning engineers. Although due to fact they are black box models, in mission critical areas (like healthcare, finance, atomic power) when explainability is required they cannot be used even when they show higher classification performance in comparison to explainable models like decision trees. To mitigate this problem knowledge extraction algorithms have been proposed allowing to extract knowledge in different forms. Current paper gives a review of three knowledge extraction algorithms, presents their strengths and weaknesses. Finally knowledge extraction workflow utilizing abovementioned algorithms is described.

Atslēgas vārdi
Artificial neural network, feedforward neural networks, knowledge acquisition, radial basis function neural networks
DOI
10.1109/ITMS.2018.8552964
Hipersaite
https://ieeexplore-ieee-org.resursi.rtu.lv/document/8552964

Bondarenko, A., Aleksejeva, L. Workflow for Knowledge Extraction from Neural Network Classifiers. No: 2018 59th International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS 2018), Latvija, Rīga, 10.-12. oktobris, 2018. Piscataway: IEEE, 2018, 57.-62.lpp. ISBN 978-1-7281-0099-9. e-ISBN 978-1-7281-0098-2. Pieejams: doi:10.1109/ITMS.2018.8552964

Publikācijas valoda
English (en)