Journal Article10.1109/jstqe.2022.3166510
All-Optical Nonlinear Activation Function Based on Germanium Silicon Hybrid Asymmetric Coupler
01 Mar 2023
- Vol. 29, Iss: 2: Optical Computing, pp 1-6
25
TL;DR: In this article , an all-optical implementation of a nonlinear activation function based on germanium silicon hybrid integration was proposed and demonstrated for optical neural networks (ONNs) to achieve more various functions.
read more
Abstract: Nonlinear activation functions are crucial for optical neural networks (ONNs) to achieve more various functions. However, the current nonlinear functions suffer from some dilemma, including high power consumption, high loss, and limited bandwidth. Here, we propose and demonstrate an all-optical implementation of a nonlinear activation function based on germanium silicon hybrid integration. The principle lies in the intrinsic absorption and the carrier-induced refractive index change of germanium in C -band. It has a large operating bandwidth and a response frequency of 70 MHz, with a loss of 4.28 dB and a threshold power of 5.1 mW. Adopting it to the MNIST handwriting data set classification, it shows an improvement in accuracy from 91.6% to 96.8%. This proves that our scheme has great potential for advanced ONN applications.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Integrated Photonic Neural Networks: Opportunities and Challenges
TL;DR: In this paper , the authors present a point of view and a suggestive roadmap in the field of integrated photonic platform for optical neural networks, highlighting recent progresses meeting with major challenges.
29
Human emotion recognition with a microcomb-enabled integrated optical neural network
Junwei Cheng,Yanzhao Xie,Yu Liu,Junjie Song,Xinyu Liu,zhenming he,Wenkai Zhang,Xinjie Han,Hailong Zhou,Ke Zhou,Heng Zhou,Jianji Dong,Xinliang Zhang +12 more
TL;DR: The proposed MIONN provides a high-speed and energy-efficient neuromorphic computing hardware for deep learning models with emotional interaction capabilities for fast and low-power computing.
21
Ultra-broadband all-optical nonlinear activation function enabled by MoTe2/optical waveguide integrated devices
Chenduan Chen,Yang Zhan,Tao Wang,Yalun Wang,Kai Gao,Jiajia Wu,Jun Wang,Jianrong Qiu,Dezhi Tan +8 more
TL;DR: Researchers integrate MoTe2 with optical waveguides to create ultra-broadband all-optical nonlinear activation functions, achieving low activation thresholds, high-density integration, and fast response rates, enabling efficient optical neural networks with applications in image recognition and classification.
8
3-Port beam splitter of arbitrary power ratio enabled by deep learning on a multimode waveguide
Zeyu Deng,Zhangqi Dang,Tao Chen,Zhengming Ding,Ziyang Zhang +4 more
TL;DR: A 3-port beam splitter with arbitrary power ratio is developed on a multimode waveguide using deep learning, enabling variable attenuation and power splitting ratios through thermally controlled microheaters and neural network optimization.
6
Microdisk modulator-assisted optical nonlinear activation functions for photonic neural networks
Bin Wang,Weizhen Yu,Jinming Duan,Shuwen Yang,Zhenyu Zhao,Shuang Zheng,Weifeng Zhang +6 more
TL;DR: Microdisk modulator-assisted optical nonlinear activation functions for photonic neural networks enable high-speed electro-optic and all-optical nonlinear activation functions in a single device.
3
References
Deep learning with coherent nanophotonic circuits
Yichen Shen,Nicholas C. Harris,Scott Skirlo,Dirk Englund,Marin Soljacic +4 more
- 01 Jul 2017
TL;DR: A new architecture for a fully optical neural network is demonstrated that enables a computational speed enhancement of at least two orders of magnitude and three order of magnitude in power efficiency over state-of-the-art electronics.
2.9K
High-performance Ge-on-Si photodetectors
TL;DR: In this article, the authors summarized the major developments in Ge-on-Si photodetectors, including epitaxial growth and strain engineering, free-space and waveguide-integrated devices, as well as recent progress in Geon-On-Si avalanche photodets.
1.5K
All-optical spiking neurosynaptic networks with self-learning capabilities.
TL;DR: An optical version of a brain-inspired neurosynaptic system, using wavelength division multiplexing techniques, is presented that is capable of supervised and unsupervised learning.
Nonlinear silicon photonics
TL;DR: In this article, a review of nonlinear effects in silicon and highlights the important applications and technological solutions in nonlinear silicon photonics is presented. But the authors do not discuss the nonlinearities in silicon.
1.3K
Parallel convolutional processing using an integrated photonic tensor core.
Johannes Feldmann,Nathan Youngblood,Nathan Youngblood,Maxim Karpov,Helge Gehring,Xuan Li,Maik Stappers,M. Le Gallo,Xin Fu,Anton Lukashchuk,Arslan S. Raja,Junqiu Liu,C.D. Wright,Abu Sebastian,Tobias J. Kippenberg,Wolfram H. P. Pernice,Harish Bhaskaran +16 more
TL;DR: In this paper, the authors demonstrate a computationally specific integrated photonic hardware accelerator (tensor core) that is capable of operating at speeds of trillions of multiply-accumulate operations per second.
1.1K
Related Papers (5)
Yasuhiko Ishikawa,Jiro Osaka,Kazumi Wada +2 more
- 01 Dec 2009
Shinichi Saito
- 01 Nov 2011