An Inside Look at Deep Neural Networks using Graph Signal Processing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

An Inside Look at Deep Neural Networks using Graph Signal Processing

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.
No file

Dates and versions

hal-01959770 , version 1 (19-12-2018)

Identifiers

Cite

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⟩
101 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More