Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Conferences > OFC > 2020 > W3A > W3A.6

Interferometer-based Photonic Circuit Classifier Showing >90% Accuracy for Well-known Iris Dataset without Utilizing Nonlinear Activation Function

Guangwei Cong, Noritsugu Yamamoto, Takashi Inoue, Yuriko Maegami, Morifumi Ohno, Makoto Okano, Shu Namiki, and Koji Yamada

Not Accessible

Your library or personal account may give you access

Abstract

We demonstrate that interferometer-based photonic circuits can perform classification by only phase control even without activation functions, which can classify well-known Iris dataset with >90% accuracy in simulation, showing simple photonic implementation for machine learning.

© 2020 The Author(s)

PDF Article
More Like This
Machine Learning Training in Silicon Photonic Circuits

Guangwei Cong, Noritsugu Yamamoto, Takashi Inoue, Yuriko Maegami, Morifumi Ohno, Shota Kita, Shu Namiki, and Koji Yamada
FM6D.2 Frontiers in Optics (FiO) 2023

On-chip Training Silicon Photonic Circuits to Perform Digital and Analog Computing

Guangwei Cong, Noritsugu Yamamoto, Yuriko Maegami, Morifumi Ohno, Shota Kita, Shu Namiki, and Koji Yamada
SS2B.1 CLEO: Science and Innovations (CLEO:S&I) 2022

Optical Nonlinear Activation Functions Based on MZI-Structure for Optical Neural Networks

Qiang Li, Shengping Liu, Yang Zhao, Wei Wang, Ye Tian, Junbo Feng, and Jin Guo
T4D.4 Asia Communications and Photonics Conference (ACP) 2020

View More...
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use