On-fiber photonic computing
In the 1800s, Charles Babbage envisioned computers as analog devices. However, it was
not until 150 years later that a Mechanical Analog Computer was constructed for the US …
not until 150 years later that a Mechanical Analog Computer was constructed for the US …
Caravan: Practical Online Learning of {In-Network}{ML} Models with Labeling Agents
Recent work on in-network machine learning (ML) anticipates offline models to operate well
in modern networking environments. However, upon deployment, these models struggle to …
in modern networking environments. However, upon deployment, these models struggle to …
Implementing the analogous neural network using chaotic strange attractors
Abstract Machine learning studies need colossal power to process massive datasets and
train neural networks to reach high accuracies, which have become gradually …
train neural networks to reach high accuracies, which have become gradually …
Architecture-level modeling of photonic deep neural network accelerators
Photonics is a promising technology to accelerate Deep Neural Networks as it can use
optical interconnects to reduce data movement energy and it enables low-energy, high …
optical interconnects to reduce data movement energy and it enables low-energy, high …
Scalable On-Chip Optoelectronic Ising Machine Utilizing Thin-Film Lithium Niobate Photonics
The Ising machine (IM) has emerged as a promising tool for tackling nondeterministic
polynomial-time hard combinatorial optimization problems in real-world applications. Among …
polynomial-time hard combinatorial optimization problems in real-world applications. Among …
First Demonstration of Real-Time Photonic-Electronic DNN Acceleration on SmartNICs
We demonstrate Lightning, a reconfigurable photonic-electronic deep learning smartNIC
that serves real-time inference requests at 4.055 GHz compute frequency. To do so …
that serves real-time inference requests at 4.055 GHz compute frequency. To do so …
OISA: Architecting an Optical In-Sensor Accelerator for Efficient Visual Computing
Targeting vision applications at the edge, in this work, we systematically explore and
propose a high-performance and energy-efficient Optical In-Sensor Accelerator architecture …
propose a high-performance and energy-efficient Optical In-Sensor Accelerator architecture …
[HTML][HTML] Vertically hierarchical electro-photonic neural network by cascading element-wise multiplication
G Cong, N Yamamoto, R Kou, Y Maegami, S Namiki… - APL Photonics, 2024 - pubs.aip.org
Integrated photonic neural networks (PNNs) usually adopt traditional convolutional neural
network (CNN) or multilayer perceptron (MLP) network models. These models consist of …
network (CNN) or multilayer perceptron (MLP) network models. These models consist of …
What comes after optical-bypass network? A study on optical-computing-enabled network
DT Hai - Optical Fiber Technology, 2024 - Elsevier
A new architectural paradigm, named, optical-computing-enabled network, is proposed as a
potential evolution of the currently used optical-bypass framework. The main idea is to …
potential evolution of the currently used optical-bypass framework. The main idea is to …
Accuracy of linear transformations performed on a nonideal Mach–Zehnder interferometer
NV Barabash, KV Sidorenko, AV Nezhdanov… - Optics …, 2024 - Elsevier
We consider a mathematical model of a planar Mach–Zehnder interferometer with nonideal
beam splitters. For this model, we obtain two fidelity estimates of the matrix–vector …
beam splitters. For this model, we obtain two fidelity estimates of the matrix–vector …