[17p-K306-1~11] FS.1 Focused Session "AI Electronics"

2:30 PM - 2:45 PM JST(5:30 AM - 5:45 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[17p-K306-4] Demonstration of handwritten digit classification using the magneto-optical diffractive neural network

〇Hotaka Sakaguchi¹, Takuma Honma¹, Satoshi Sumi², Hiroyuki Awano², Hirofumi Nonaka³, Fatima Zahra Chafi¹, Takayuki Ishibashi¹ (1.Nagaoka Univ. of Tech., 2.Toyota Tech. Inst., 3.Aichi Inst. of Tech.)

Keywords:

optical computing,magneto-optical effect,Neuromorphic computing

To solve the energy consumption problem of deep neural network, we have studied on the development of a magneto-optical diffractive deep neural network (MO-D²NN) that utilize the magneto-optical effect of magnetic material. In our previous work, we reported the fabrication of hidden layer of MO-D²NN using thermomagnetic recording techniques on Bi-substitued iron garnet film, which exhibits large magneto-optical effect. In this report, we present the experimental demonstration of handwritten digit classification using the MO-D²NN.