返回
Microring-based programmable coherent optical neural networks
DOI:10.1364/OE.492551.png)
摘要
En 中文
Coherent programmable integrated photonics circuits have shown great potential as specialized hardware accelerators for deep learning tasks, which usually involve the use of linear matrix multiplication and nonlinear activation components. We design, simulate and train an optical neural network fully based on microring resonators, which shows advantages in terms of device footprint and energy efficiency. We use tunable coupled double ring structures as the interferometer components for the linear multiplication layers and modulated microring resonators as the reconfigurable nonlinear activation components. We then develop optimization algorithms to train the direct tuning parameters such as applied voltages based on the transfer matrix method and using automatic differentiation for all optical components. & COPY; 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
Keyword:
EXPERIMENTAL REALIZATION
ARTIFICIAL-INTELLIGENCE
SILICON
PHOTONICS
DESIGN
期刊
IF:
3.3
论文数:
6.1W
被引数:
14.3W
机构
引用论文
HKUST-1 Metal–Organic Framework Nanoparticle/Graphene Oxide Nanocomposite Aerogels for CO2 and CH4 Adsorption and SeparationHKUST-1金属有机骨架纳米颗粒/氧化石墨烯纳米复合气凝胶用于CO2 和CH4 吸附分离
Large-scale silicon quantum photonics implementing arbitrary two-qubit processing实现任意两量子位处理的大规模硅量子光子学
NATURE PHOTONICS
IF32.9
Resolving the thermal challenges for silicon microring resonator devices解决硅微环谐振器器件的热挑战
NANOPHOTONICS
IF6.6
The cathodic behavior of microwave-treated manganese dioxide in lithium nonaqueous cells微波处理的二氧化锰在非水锂电池中的阴极行为
Photonics for artificial intelligence and neuromorphic computing用于人工智能和神经形态计算的光子学
NATURE PHOTONICS
IF32.9

