Dependence of activation function on image recognition accuracy in self-referential holographic deep neural network

Rio Tomioka; Masanori Takabayashi; Masanori Takabayashi

Proceedings of the 2022 International Symposium on Imaging, Sensing, and Optical Memory (ISOM) and the 13th International Conference on Optics-photonics Design and Fabrication (ODF)
Technical Digest Series (Optica Publishing Group, 2022),
paper ITuPJ_01

Dependence of activation function on image recognition accuracy in self-referential holographic deep neural network

Rio Tomioka and Masanori Takabayashi

International Symposium on Imaging, Sensing, and Optical Memory 2022

Sapporo Japan
31 August–5 September 2022
ISBN:

From the session
Optical Information (ITuPJ)

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
R. Tomioka and M. Takabayashi, "Dependence of activation function on image recognition accuracy in self-referential holographic deep neural network," in Proceedings of the 2022 International Symposium on Imaging, Sensing, and Optical Memory (ISOM) and the 13th International Conference on Optics-photonics Design and Fabrication (ODF), Technical Digest Series (Optica Publishing Group, 2022), paper ITuPJ_01.

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Save article

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.

PDF Article

More Like This

Single and shift-multiplexing recording properties in self-referential holographic data storage with designed additional pattern

Kazuki Chijiwa and Masanori Takabayashi
P_ITu_20 International Symposium on Imaging, Sensing, and Optical Memory (ODS) 2022

Proposal of ReLU activation function using III-V semiconductor membrane laser for optical neural network

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

All-optical, ultrafast energy-efficient ReLU function for nanophotonic neural networks

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

Previous Article Next Article