Skip to Main content Skip to Navigation
Conference papers

An Inside Look at Deep Neural Networks using Graph Signal Processing

Vincent Gripon 1 Antonio Ortega 2 Benjamin Girault 2 
1 IMT Atlantique - ELEC - Département Electronique
2 Signal and Image Processing Institute
Abstract : Deep Neural Networks (DNNs) are state-of-the-art in many machine learning benchmarks. Understanding how they perform is a major open question. In this paper, we are interested in using graph signal processing to monitor the intermediate representations obtained in a simple DNN architecture. We compare different metrics and measures and show that smoothness of label signals on k-nearest neighbor graphs are a good candidate to interpret individual layers role in achieving good performance.
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/hal-01959770
Contributor : Benjamin Girault Connect in order to contact the contributor
Submitted on : Wednesday, December 19, 2018 - 1:23:57 AM
Last modification on : Monday, April 4, 2022 - 9:28:18 AM

Identifiers

Collections

INSTITUT-TELECOM | IMT-ATLANTIQUE

Citation

Vincent Gripon, Antonio Ortega, Benjamin Girault. An Inside Look at Deep Neural Networks using Graph Signal Processing. 2018 Information Theory and Applications Workshop (ITA), Feb 2018, San Diego, CA, United States. pp.1-9, ⟨10.1109/ITA.2018.8503214⟩. ⟨hal-01959770⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

74

 

Contact                    Legal Notice                    Personal Data