Improving neural network interpretability via rule extraction
2018
Files
Abstract
We present a method to replace the fully-connected layers of a Convolutional Neural Network (CNN9 with a small set of rules, allowing for better interpretation of its decisions while preserving accuracy.
Details
Title
Improving neural network interpretability via rule extraction
Author(s)
Gomez Schnyder, Stéphane (School of Management and Engineering Vaud, HES-SO University of Applied Sciences Western Switzerland ; Computational Intelligence for Computational Biology (CI4CB), SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland)
Despraz, Jérémie (School of Management and Engineering Vaud, HES-SO University of Applied Sciences Western Switzerland ; Computational Intelligence for Computational Biology (CI4CB), SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland)
Peña-Reyes, Carlos Andrés (School of Management and Engineering Vaud, HES-SO University of Applied Sciences Western Switzerland ; Computational Intelligence for Computational Biology (CI4CB), SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland)
Despraz, Jérémie (School of Management and Engineering Vaud, HES-SO University of Applied Sciences Western Switzerland ; Computational Intelligence for Computational Biology (CI4CB), SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland)
Peña-Reyes, Carlos Andrés (School of Management and Engineering Vaud, HES-SO University of Applied Sciences Western Switzerland ; Computational Intelligence for Computational Biology (CI4CB), SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland)
Date
2018-10
Published in
Proceedings Part I of Artificial Neural Networks and Machine Learning – ICANN 2018, 27th International Conference on Artificial Neural Networks, 4-7 October 2018, Rhodes, Greece
Volume
pp. 811-813
Publisher
Rhodes, Greece, 4-7 October 2018
Pagination
3 p.
Presented at
Artificial Neural Networks and Machine Learning – ICANN 2018, 27th International Conference on Artificial Neural Networks, Rhodes, Greece, 2018-10-04, 2018-10-07
Keywords
convolutional neural network ; deep-learning rule extraction ; random forests ; interpretability
Paper type
short paper
Faculty
Ingénierie et Architecture
School
HEIG-VD
Institute
IICT - Institut des Technologies de l'Information et de la Communication
Record Appears in
Conference materials
Global
Global