Presentation Information
[19p-P06-5]Optimization of Magneto-Optical Diffraction Deep Neural Networks
〇(M1C)Reo Akagawa1, Hotaka Sakaguchi1, Hirofumi Nonaka2, Hiroyuki Awano3, Fatima Zahara Chafi1, Takayuki Ishibashi1 (1.Nagaoka Univ. Tech., 2.Aichi Inst. Tech., 3.Toyota Tech. Inst.)
Keywords:
Deep Neural Network,optics,Magneto optical effect
In recent years, Deep Neural Network (DNN) have attracted attention, achieved rapid development, and been applied in various fields. However, the increase in processing speed and power consumption for complex models has become a problem. To solve these problems, we have proposed a magneto-optical diffractive deep neural network (MO-D2NN) that utilizes the magneto-optical effect. However, MO-D2NN has many parameters to be considered. Therefore, in this study, we evaluated the performance of MO-D2NN by varying the distance between each layer.