Zobrazeno 1 - 10
of 377
pro vyhledávání: '"Optical neural networks"'
Autor:
Bahr, Niklas, Dijkstra, Jelle, Brückerhoff-Plückelmann, Frank, Bente, Ivonne, Wendland, Daniel, Pernice, Wolfram
Novel photonic compute hardware is a rising and promising technology wherever low-latency or energy efficient computation is required. Especially, optical neural networks (ONNs) aim to provide accelerators for artificial intelligence (AI) application
Externí odkaz:
https://htwk-leipzig.qucosa.de/id/qucosa%3A94313
https://htwk-leipzig.qucosa.de/api/qucosa%3A94313/attachment/ATT-0/
https://htwk-leipzig.qucosa.de/api/qucosa%3A94313/attachment/ATT-0/
Publikováno v:
Results in Physics, Vol 65, Iss , Pp 107968- (2024)
We propose an on-chip photoelectric hybrid convolution accelerator based on Bragg grating array. The weight of the convolution kernel can be adjusted by controlling the central wavelengths of the Bragg grating array. We conducted simulation verificat
Externí odkaz:
https://doaj.org/article/cb5995e980b5401ca22076d944558e32
Publikováno v:
Advanced Photonics Research, Vol 5, Iss 6, Pp n/a-n/a (2024)
Diffractive neural networks (DNNs) are emerging as a new machine learning hardware based on optical diffraction with parallel and high‐throughput information processing. The optical inputs to DNNs are spatially modulated by propagating through pass
Externí odkaz:
https://doaj.org/article/51272258404743e08a909da0703deafa
Autor:
Cong He, Dan Zhao, Fei Fan, Hongqiang Zhou, Xin Li, Yao Li, Junjie Li, Fei Dong, Yin-Xiao Miao, Yongtian Wang, Lingling Huang
Publikováno v:
Opto-Electronic Advances, Vol 7, Iss 2, Pp 1-9 (2024)
Optical neural networks have significant advantages in terms of power consumption, parallelism, and high computing speed, which has intrigued extensive attention in both academic and engineering communities. It has been considered as one of the power
Externí odkaz:
https://doaj.org/article/4ef1d339d098499280f9566596947025
Autor:
Minjoo Kim, Beomju Kim, Yelim Kim, Lia Saptini Handriani, Suhee Jang, Dae Yeop Jeong, Sung Ik Yang, Won Il Park
Publikováno v:
IEEE Photonics Journal, Vol 16, Iss 2, Pp 1-8 (2024)
We developed an optical neural network (ONN) for efficient processing and recognition of 2-dimensional (2D) images, employing a conventional liquid crystal display panel as optical neurons and synapses. This configuration allowed for optical signal o
Externí odkaz:
https://doaj.org/article/69e5d1667232481091051d93521e2f38
Publikováno v:
IET Optoelectronics, Vol 17, Iss 4, Pp 175-183 (2023)
Abstract Visible light communication can be leveraged to establish a wireless link between neurons in spiking networks even when neural areas are in relative motions. In electro‐optical spiking neural networks (SNN), parallel transmission is often
Externí odkaz:
https://doaj.org/article/a18ec792433a43f2812e179f215baf88
Publikováno v:
Advanced Photonics Research, Vol 5, Iss 2, Pp n/a-n/a (2024)
Neural network accelerator based on photonic‐integrated circuits is emerging as a promising technology for fast, power‐efficient, and parallel computing. Under such technology, optics is mainly used for linear transformations, e.g., through an ar
Externí odkaz:
https://doaj.org/article/82979eb48f7148c38bb1cb63d908b7e4
Autor:
Jiangtao Lv, Ruizhe Zhang, Qiongchan Gu, Md Hemayet Uddin, Xiaoxiao Jiang, Junqiao Qi, Guangyuan Si, Qingdong Ou
Publikováno v:
Materials & Design, Vol 237, Iss , Pp 112610- (2024)
Metasurfaces exhibit excellent performance in the regulation of optical field parameters, such as phase, amplitude, and polarization, by using nanounit structures. The characteristics of metasurface miniaturization and its combination with advanced s
Externí odkaz:
https://doaj.org/article/f8b8be1460954c6d91444fec88b93186
Publikováno v:
Advanced Intelligent Systems, Vol 5, Iss 12, Pp n/a-n/a (2023)
Diffractive optical neural networks (DONNs) are emerging as high‐throughput and energy‐efficient hardware platforms to perform all‐optical machine learning (ML) in machine vision systems. However, the current demonstrated applications of DONNs
Externí odkaz:
https://doaj.org/article/2591c4993f0b495a9f2c6e2249faa3dd
Autor:
Marlon Becker, Jan Riegelmeyer, Maximilian David Seyfried, Bart Jan Ravoo, Carsten Schuck, Benjamin Risse
Publikováno v:
Advanced Intelligent Systems, Vol 5, Iss 12, Pp n/a-n/a (2023)
Optical neural networks (ONNs) hold great potential for faster and more energy‐efficient information processing in coherent photonic circuits. To realize ONNs, linear combinations and nonlinear activation functions have to be implemented in an opti
Externí odkaz:
https://doaj.org/article/f34e4f2fa14a4fdc8c5da3713f126287