Abstract
We numerically compared the image recognition properties of self-referential holographic deep neural network (SR-HDNN) with various activation functions. The image recognition rate was improved to 87.1% by applying intensity-ReLU function to SR-HDNN.
© 2022 IEEE
PDF ArticleMore Like This
Kazuki Chijiwa and Masanori Takabayashi
P_ITu_20 International Symposium on Imaging, Sensing, and Optical Memory (ODS) 2022
Naoki Takahashi, Weicheng Fang, Ruihao Xue, Shunto Katsumi, Yoshitaka Ohiso, Tomohiro Amemiya, and Nobuhiko Nishiyama
CMP11B_02 Conference on Lasers and Electro-Optics/Pacific Rim (CLEO/PR) 2022
Gordon H.Y. Li, Ryoto Sekine, Rajveer Nehra, Robert M. Gray, Luis Ledezma, Qiushi Guo, and Alireza Marandi
STh5G.6 CLEO: Science and Innovations (CLEO:S&I) 2022