Photonic Max-Pooling for Deep Neural Networks Using a Programmable Photonic Platform

被引：4

作者：

Ashtiani, Farshid ^{[1
]}

On, Mehmet Berkay ^{[1
,2
]}

Sanchez-Jacome, David ^{[3
]}

Perez-Lopez, Daniel ^{[3
]}

Yoo, S. J. Ben ^{[2
]}

Blanco-Redondo, Andrea ^{[1
]}

机构：

[1] Nokia Bell Labs, 600 Mt Ave, Murray Hill, NJ 07974 USA

[2] Univ Calif Davis, Dept Elect & Comp Engn, 1 Shields Ave, Davis, CA 95616 USA

[3] iPron Programmable Photon, Avenida Blasco Ibanez 25, Valencia 46010, Spain

来源：

2023 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXHIBITION, OFC | 2023年

关键词：

D O I：

10.1364/OFC.2023.M1J.6

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We propose a photonic max-pooling architecture for photonic neural networks which is compatible with integrated photonic platforms. As a proof of concept, we have experimentally demonstrated the max-pooling function on a programmable photonic platform consisting of a hexagonal mesh of Mach-Zehnder interferometers. (C) 2022 The Author(s)

引用

页数：3

共 50 条

[41] Experimentally realized in situ backpropagation for deep learning in photonic neural networks
Pai, Sunil
Sun, Zhanghao
Hughes, Tyler W.
Park, Taewon
Bartlett, Ben
Williamson, Ian A. D.
Minkov, Momchil
Milanizadeh, Maziyar
Abebe, Nathnael
Morichetti, Francesco
Melloni, Andrea
Fan, Shanhui
Solgaard, Olav
Miller, David A. B.
SCIENCE, 2023, 380 (6643) : 398 - 403
[42] Photonic neural networks and optics-informed deep learning fundamentals
Tsakyridis, Apostolos
Moralis-Pegios, Miltiadis
Giamougiannis, George
Kirtas, Manos
Passalis, Nikolaos
Tefas, Anastasios
Pleros, Nikos
APL PHOTONICS, 2024, 9 (01)
[43] Deep Neural Networks with Time-Domain Synthetic Photonic Lattices
Pankov, Artem, V
Sidelnikov, Oleg S.
Vatnik, Ilya D.
Churkin, Dmitry, V
Sukhorukov, Andrey A.
2021 CONFERENCE ON LASERS AND ELECTRO-OPTICS EUROPE & EUROPEAN QUANTUM ELECTRONICS CONFERENCE (CLEO/EUROPE-EQEC), 2021,
[44] Efficient Two-Stage Max-Pooling Engines for an FPGA-Based Convolutional Neural Network
Hong, Eonpyo
Choi, Kang-A
Joo, Jhihoon
ELECTRONICS, 2023, 12 (19)
[45] Integrated programmable photonic filter on the silicon-on-insulator platform
Liao, Shasha
Ding, Yunhong
Peucheret, Christophe
Yang, Ting
Dong, Jianji
Zhang, Xinliang
OPTICS EXPRESS, 2014, 22 (26): : 31993 - 31998
[46] Universal Optical Logic Gates on a Programmable Silicon Photonic Platform
Ashtiani, Farshid
2024 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXHIBITION, OFC, 2024,
[47] Area and Energy Efficient 2D Max-Pooling For Convolutional Neural Network Hardware Accelerator
Zhao, Bin
Chong, Yi Sheng
Anh Tuan Do
IECON 2020: THE 46TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2020, : 423 - 427
[48] CS-LoFT: Color and Scale Adaptive Tracking Using Max-Pooling With Bhattacharyya Distance
AL-Shakarji, Noor M.
Bunyak, Filiz
Seetharaman, Guna
Palaniappan, Kannappan
2016 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2016,
[49] Optimizing photonic devices under fabrication variations with deep photonic networks
Gorgulu, Kazim
Vit, Aycan Deniz
Amiri, Ali Najjar
Magden, Emir Salih
SILICON PHOTONICS XIX, 2024, 12891
[50] Opportunities for integrated photonic neural networks
Stark, Pascal
Horst, Folkert
Dangel, Roger
Weiss, Jonas
Offrein, Bert Jan
NANOPHOTONICS, 2020, 9 (13) : 4221 - 4232

← 1 2 3 4 5 →