[1P] Late-Breaking Abstracts

[1P-466] Constraining Representations to Multiple Spontaneous Activity States Improves Robustness of the Artificial Neural Networks

*Motoki Sato^1,2,3, Takehiro Ajioka^1,2,3, Kenichi Ohki^1,2,3 (1. Department of Physiology, Graduate School of Medicine, The University of Tokyo, 2. International Research Center for Neurointelligence (IRCN), The University of Tokyo, 3. Institute for AI and Beyond, The University of Tokyo)

Keywords:

SPONTANEOUS ACTIVITY,ADVERSARIAL ATTACK,DEEP LAERNING,VISUAL RECOGNITION

Password required to view

A password is required to view the abstracts.
The password can be found on your name badge (participation certificate).