Improving neural network interpretability via rule extraction
2018
Résumé
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.
Einzelheiten
Titel
Improving neural network interpretability via rule extraction
Autor(en)/ in(nen)
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)
Datum
2018-10
Veröffentlich 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
Band
pp. 811-813
Verlag
Rhodes, Greece, 4-7 October 2018
Umfang
3 p.
Vorgestellt auf
Artificial Neural Networks and Machine Learning – ICANN 2018, 27th International Conference on Artificial Neural Networks, Rhodes, Greece, 2018-10-04, 2018-10-07
Schlüsselwörter
convolutional neural network ; deep-learning rule extraction ; random forests ; interpretability
Papiertyp
short paper
Domaine
Ingénierie et Architecture
Ecole
HEIG-VD
Institut
IICT - Institut des Technologies de l'Information et de la Communication
Das Dokument erscheint in
Konferenzmaterialien
Global
Global