Analog nanophotonic computing going practical: silicon photonic deep learning engines for tiled optical matrix multiplication with dynamic precision
Analog photonic computing comprises a promising candidate for accelerating the linear
operations of deep neural networks (DNNs), since it provides ultrahigh bandwidth, low …
operations of deep neural networks (DNNs), since it provides ultrahigh bandwidth, low …
Universal linear optics revisited: new perspectives for neuromorphic computing with silicon photonics
G Giamougiannis, A Tsakyridis… - IEEE Journal of …, 2022 - ieeexplore.ieee.org
Reprogrammable optical meshes comprise a subject of heightened interest for the execution
of linear transformations, having a significant impact in numerous applications that extend …
of linear transformations, having a significant impact in numerous applications that extend …
Photonic neural networks and optics-informed deep learning fundamentals
The recent explosive compute growth, mainly fueled by the boost of artificial intelligence (AI)
and deep neural networks (DNNs), is currently instigating the demand for a novel computing …
and deep neural networks (DNNs), is currently instigating the demand for a novel computing …
Scaling photonic neural networks: A silicon photonic GeMM leveraging a Time-Space multiplexed Xbar
S Kovaios, I Roumpos, M Moralis-Pegios… - Journal of Lightwave …, 2024 - ieeexplore.ieee.org
We demonstrate a silicon photonic Xbar-based general matrix multiplier (Xbar GeMM) for
optical neural network (NN) applications, utilizing a hybrid time-space multiplexing scheme …
optical neural network (NN) applications, utilizing a hybrid time-space multiplexing scheme …
Generalized Mach Zehnder Interferometers Integrated on Si3N4 Waveguide Platform
S Kovaios, A Tsakyridis… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
We demonstrate 3× 3 and 4× 4 Generalized Mach Zehnder Interferometers (GMZI)
integrated on the Si 3 N 4 waveguide platform and present their experimental performance …
integrated on the Si 3 N 4 waveguide platform and present their experimental performance …
[PDF][PDF] 插损鲁棒性的全复值光学神经网络
陈慧彬， 汤凯飞， 游振宇 - 中国光学(中英文), 2024 - chineseoptics.net.cn
基于马赫-曾德尔干涉仪(Mach-Zehnder Interferometer, MZI) 级联拓扑结构的线性光学处理器被
证明是实现光学神经网络(Optical Neural Network, ONN) 的重要途径, 但还有不少实际问题有待 …
证明是实现光学神经网络(Optical Neural Network, ONN) 的重要途径, 但还有不少实际问题有待 …
Optics-informed neural networks towards accelerating linear operations
A Tsakyridis, M Moralis-Pegios… - Optical …, 2024 - spiedigitallibrary.org
The recent explosive compute growth, mainly fueled by the boost of artificial intelligence (AI)
and deep neural networks (DNNs), is currently instigating the demand for a novel computing …
and deep neural networks (DNNs), is currently instigating the demand for a novel computing …
Quantum Interference Patterns for N-Photon States Using a Gires-Tournois Etalon Assisted Dual-Pass Mach-Zehnder Interferometer
Quantum Interference Patterns for N-Photon States Using a Gires-Tournois Etalon Assisted
Dual-Pass Mach-Zehnder Interferometer Page 1 XXX-X-XXXX-XXXX-X/XX/$XX.00 ©20XX IEEE …
Dual-Pass Mach-Zehnder Interferometer Page 1 XXX-X-XXXX-XXXX-X/XX/$XX.00 ©20XX IEEE …
A 4x4 Si3N4 generalized Mach-Zehnder interferometer for variable power splitting applications
S Kovaios, K Fotiadis, A Tsakyridis… - Optical …, 2023 - spiedigitallibrary.org
Rapid developments in computer science have led to the increasing demand for efficient
computing systems. Linear photonic systems rose as a favorable candidate for workload …
computing systems. Linear photonic systems rose as a favorable candidate for workload …
Fidelity-Restorable Universal Linear Optics and Neuromorphic Photonics
Universal linear operators realized in photonics are expected to drive the next wave of ultra-
high throughput neuromorphic computing. We present integrated photonic solutions for …
high throughput neuromorphic computing. We present integrated photonic solutions for …