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.
|Title of host publication||ICINCO 2020 - Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics|
|Editors||Oleg Gusikhin, Kurosh Madani, Janan Zaytoon|
|Number of pages||6|
|Publication status||Published - 2020|
|Event||17th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2020 - Virtual, Online, France|
Duration: 2020 Jul 7 → 2020 Jul 9
|Name||ICINCO 2020 - Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics|
|Conference||17th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2020|
|Period||20/7/7 → 20/7/9|
Bibliographical noteFunding Information:
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (2017R1D1A1B03036172).
Copyright © 2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.
All Science Journal Classification (ASJC) codes
- Information Systems
- Control and Systems Engineering