☆ 4.7 Article

Performing photonic nonlinear computations by linear operations in a high-dimensional space

NANOPHOTONICS (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

All-Optical Nonlinear Activation Function Based on Germanium Silicon Hybrid Asymmetric Coupler

Hengkang Li et al.

Summary: Nonlinear activation functions are crucial for optical neural networks (ONNs) to achieve more various functions. However, the current nonlinear functions suffer from some dilemma, including high power consumption, high loss, and limited bandwidth. Here, we propose and demonstrate an all-optical implementation of a nonlinear activation function based on germanium silicon hybrid integration. The principle lies in the intrinsic absorption and the carrier-induced refractive index change of germanium in C -band. It has a large operating bandwidth and a response frequency of 70 MHz, with a loss of 4.28 dB and a threshold power of 5.1 mW. Adopting it to the MNIST handwriting data set classification, it shows an improvement in accuracy from 91.6% to 96.8%. This proves that our scheme has great potential for advanced ONN applications.

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS (2023)

Add to Collection

Article Materials Science, Multidisciplinary

Low-threshold all-optical nonlinear activation function based on a Ge/Si hybrid structure in a microring resonator

Bo Wu et al.

Summary: This article introduces the importance of optical nonlinear activation functions in optical neural networks. It addresses the challenges of implementing nonlinear activation functions on a chip and proposes a solution using the Ge/Si hybrid structure. Experimental results demonstrate different types of nonlinear functions and their application in a classification task for handwritten digit image datasets, showing the potential of this approach in future optical neural networks.

OPTICAL MATERIALS EXPRESS (2022)

Add to Collection

Review Optics

Photonic matrix multiplication lights up photonic accelerator and beyond

Hailong Zhou et al.

Summary: Photonic matrix multiplication is a crucial part of information processing in science and technology, offering faster and more efficient computations in the optical domain. Recent research has shown its potential for applications in telecommunications and artificial intelligence that are beyond the capabilities of conventional processors.

LIGHT-SCIENCE & APPLICATIONS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A programmable diffractive deep neural network based on a digital-coding metasurface array

Che Liu et al.

Summary: This article introduces a programmable diffractive deep neural network based on a multi-layer digital-coding metasurface array, which can be used for deep learning tasks in wave sensing and wireless communications.

NATURE ELECTRONICS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A small microring array that performs large complex-valued matrix-vector multiplication

Junwei Cheng et al.

Summary: In this paper, a systematic solution is proposed to extend photonic complex matrix-vector multiplication from the real-valued field to the complex-valued field, and support arbitrary large-scale and complex-valued matrix computation. Experimental results demonstrate the potential of the proposed solution in signal processing and artificial intelligence computing.

FRONTIERS OF OPTOELECTRONICS (2022)

Add to Collection

Article Multidisciplinary Sciences

Terahertz pulse shaping using diffractive surfaces

Muhammed Veli et al.

Summary: Recent advances in deep learning have provided non-intuitive solutions to inverse problems in optics. Diffractive networks merge wave-optics with deep learning to design task-specific elements for all-optically performing tasks like object classification. The authors present a diffractive network used to shape broadband pulses into desired optical waveforms, demonstrating direct pulse shaping in the terahertz spectrum.

NATURE COMMUNICATIONS (2021)

Add to Collection

Article Optics

Ensemble learning of diffractive optical networks

Md Sadman Sakib Rahman et al.

Summary: Researchers in the USA have made significant improvements in the performance of diffractive optical networks, signaling a major advancement in their use for optics-based computation and machine learning. By utilizing feature engineering and ensemble learning, they were able to substantially enhance the statistical inference capabilities of these networks.

LIGHT-SCIENCE & APPLICATIONS (2021)

Add to Collection

Review Optics

Photonics for artificial intelligence and neuromorphic computing

Bhavin J. Shastri et al.

Summary: Research in photonic computing is thriving due to the proliferation of optoelectronic components in photonic integration platforms. Photonic integrated circuits have enabled ultrafast artificial neural networks, with algorithms running on such hardware having the potential to address the growing demand for machine learning and artificial intelligence. Neuromorphic photonics offers sub-nanosecond latencies, providing a complementary opportunity to extend the domain of artificial intelligence.

NATURE PHOTONICS (2021)

Add to Collection

Article Multidisciplinary Sciences

Freely scalable and reconfigurable optical hardware for deep learning

Liane Bernstein et al.

Summary: The article discusses the trend of growing deep neural network models for higher accuracy and complexity, proposing a digital optical neural network (DONN) to overcome scaling limitations of traditional processors. Experimental results show that optical multicast is effective in image classification.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Optics

Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit

Tiankuang Zhou et al.

Summary: Researchers propose a reconfigurable diffractive processing unit based on the diffraction of light, which supports different neural networks and achieves high model complexity with millions of neurons. By developing an adaptive training approach to overcome system errors, they achieve excellent experimental accuracies for high-speed image and video recognition.

NATURE PHOTONICS (2021)

Add to Collection

Article Nanoscience & Nanotechnology

Self-Configuring and Reconfigurable Silicon Photonic Signal Processor

Hailong Zhou et al.

ACS PHOTONICS (2020)

Add to Collection

Article Optics

Reconfigurable all-optical nonlinear activation functions for neuromorphic photonics

Aashu Jha et al.

OPTICS LETTERS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

All-Optical 2 x 2-Bit Multiplier at 40 Gb/s Based on Canonical Logic Units-based Programmable Logic Array (CLUs-PLA)

Wenchan Dong et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2020)

Add to Collection

Review Multidisciplinary Sciences

Programmable photonic circuits

Wim Bogaerts et al.

NATURE (2020)

Add to Collection

Article Physics, Applied

Enhanced optical Kerr nonlinearity of graphene/Si hybrid waveguide

Qi Feng et al.

APPLIED PHYSICS LETTERS (2019)

Add to Collection

Article Optics

Novel frontier of photonics for data processing-Photonic accelerator

Ken-ichi Kitayama et al.

APL PHOTONICS (2019)

Add to Collection

Article Optics

Integrated all-optical programmable logic array based on semiconductor optical amplifiers

Wenchan Dong et al.

OPTICS LETTERS (2018)

Add to Collection

Article Optics

Reinforcement learning in a large-scale photonic recurrent neural network

J. Bueno et al.

OPTICA (2018)

Add to Collection

Article Nanoscience & Nanotechnology

Adjoint Method and Inverse Design for Nonlinear Nanophotonic Devices

Tyler W. Hughes et al.

ACS PHOTONICS (2018)

Add to Collection

Review Optics

Linear programmable nanophotonic processors

Nicholas C. Harris et al.

OPTICA (2018)

Add to Collection

Article Optics

Deep learning with coherent nanophotonic circuits

Yichen Shen et al.

NATURE PHOTONICS (2017)

Add to Collection

Article Multidisciplinary Sciences

Neuromorphic photonic networks using silicon photonic weight banks

Alexander N. Tait et al.

SCIENTIFIC REPORTS (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Microring Weight Banks

Alexander N. Tait et al.

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS (2016)

Add to Collection

News Item Multidisciplinary Sciences

THE SEMICONDUCTOR INDUSTRY WILL SOON ABANDON ITS PURSUIT OF MOORE'S LAW. NOW THINGS COULD GET A LOT MORE INTERESTING

M. Mitchell Waldrop

NATURE (2016)

Add to Collection

Article Optics

40 Gb/s reconfigurable optical logic gates based on FWM in silicon waveguide

Jie Hou et al.

OPTICS EXPRESS (2016)

Add to Collection

Article Optics

High-speed all-optical NAND/AND logic gates using four-wave mixing Bragg scattering

Kangmei Li et al.

OPTICS LETTERS (2016)

Add to Collection

Article Optics

Optimal design for universal multiport interferometers

William R. Clements et al.

OPTICA (2016)

Add to Collection

Article Optics

Optical half-adder and half-subtracter employing the Pockels effect

Haowei Jiang et al.

OPTICS EXPRESS (2015)

Add to Collection

Article Optics

Ultrafast surface plasmon-polariton logic gates and half-adder

Tobias Birr et al.

OPTICS EXPRESS (2015)

Add to Collection

Article Optics

Canonical logic units using bidirectional four-wave mixing in highly nonlinear fiber

W. C. Dong et al.

PHOTONICS RESEARCH (2015)

Add to Collection

© Peeref 2019-2024. All rights reserved.