[22p-A302-1~15] FS.1 Focused Session "AI Electronics"

3:45 PM - 4:00 PM JST(6:45 AM - 7:00 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[22p-A302-11] Experiments on physical deep learning based on optimal control with direct feedback alignment

〇Rin Nogami¹, Kazutaka Kanno¹, Tomoaki Niiyama², Satoshi Sunada², Atsushi Uchida¹ (1.Saitama Univ., 2.Kanazawa Univ)

Keywords:

Photonic computing,Deep learning

Physical implementations of machine learning have been studied. Among them, physical deep learning based on optimal control using time-delay dynamical systems has been reported. In addition, learning can be simplified by using a technique called direct feedback alignment. This study demonstrates deep physical learning based on optimal control using direct feedback alignment.