Analyzing decision polygons of DNN-based classification methods

Jongyoung Kim, Seongyoun Woo, Wonjun Lee, Donghwan Kim, Chulhee Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep neural networks have shown impressive performance in various applications, including many pattern recognition problems. However, their working mechanisms have not been fully understood and adversarial examples indicate some fundamental problems with DNN-based classification methods. In this paper, we investigate the decision modeling mechanism of deep neural networks, which use the ReLU function. We derive some equations that show how each layer of deep neural networks expands the input dimension into higher dimensional spaces and generates numerous decision polygons. In this paper, we investigate the decision polygon formulations and present some examples that show interesting properties of DNN based classification methods.

Original languageEnglish
Title of host publicationICINCO 2020 - Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics
EditorsOleg Gusikhin, Kurosh Madani, Janan Zaytoon
PublisherSciTePress
Pages346-351
Number of pages6
ISBN (Electronic)9789897584428
Publication statusPublished - 2020
Event17th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2020 - Virtual, Online, France
Duration: 2020 Jul 72020 Jul 9

Publication series

NameICINCO 2020 - Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics

Conference

Conference17th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2020
CountryFrance
CityVirtual, Online
Period20/7/720/7/9

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Analyzing decision polygons of DNN-based classification methods'. Together they form a unique fingerprint.

Cite this