检索结果-内蒙古大学图书馆

All-optical implementation of an optoelectronic oscillator reservoir computer with an integrated spatial photonic processor

引用

OPTICS LETTERS 2025年第7期50卷 2338-2341页

作者： Tang, Dengfei Liang, En Zhao, Haibin Li, Ziwei Fudan Univ Dept Phys State Key Lab Surface Phys Shanghai 200433 Peoples R China Fudan Univ Key Lab Micro & Nano Photon Struct Minist Educ Shanghai 200433 Peoples R China Fudan Univ Shanghai Ultraprecis Opt Mfg Engn Res Ctr Dept Opt Sci & Engn Shanghai 200433 Peoples R China Fudan Univ Key Lab Informat Sci Electromagnet Waves MoE Shanghai 200433 Peoples R China

Reservoir computing (RC), inspired by neural networks, has gained significant attention for tackling complex tasks such as recognition and classification. Most RC implementations are limited to software, which restricts processing speed, as reservoir outputs are often processed through slow, digital offline post-processing in previous work. To address these constraints, we propose a solution that combines a nonlinear time-delayed optoelectronic oscillator (OEO) with an integrated spatial photonic processor (ISPP) for online reservoir output processing. This approach leverages both temporal multiplexing and spatial processing, enabling highspeed, and parallel hardware implementation. We achieve enhanced performance in modulation format recognition (MFR) for visible light communication (VLC) signals using a photonic reservoir with 64 nodes. Tests on 16 widely used modulation formats at a 2 Gbps data rate over a 1.2 m VLC transmission link demonstrate that this spatiotemporal multiplexing technique can accurately classify all formats, achieving a state-of-the-art overall accuracy of 99.5%. (c) 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： neural networks optical networks optical neural systems Signal transmission Visible light communications Wavelength division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Recurrent neural networks and Recurrent optical Spectrum Slicers as Equalizers in High Symbol Rate optical Transmission Systems

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2023年第15期41卷 5037-5050页

作者： Sozos, Kostas Deligiannidis, Stavros Sarantoglou, George Mesaritakis, Charis Bogris, Adonis Univ West Attica Dept Informat & Comp Engn Egaleo 12243 Greece Univ Aegean Dept Informat & Commun Syst Engn Samos 83200 Greece

The transition to the edge-cloud era makes ultra-high data rate signals indispensable for covering the immense and increasing traffic demands created. This ecosystem also seeks for power efficient optical modules that will deliver this enormous data load. optical communication systems and their continuous evolution have responded to the upward trend of capacity needs in all different network ecosystems, scaling from short-reach links serving data center, fiber-to-the-home and 5G/B5G services to metro and long-haul transoceanic cables. Kerr induced non-linearities at long haul and dispersion induced power fading at short reach remain intractable problems that vastly affect high symbol rate systems. So, they must be addressed in a power efficient way in order to cope with the ever-increasing traffic requirements. In this article, we review our recent work in machine learning and neuromorphic processing in the optical domain for the mitigation of transmission impairments at very high symbol rates. Post-detection techniques based on bidirectional recurrent neural networks for non-linearity compensation and neuromorphic recurrent optical spectrum slicers for power fading mitigation and self-coherent detection emerge as promising solutions for mid-term deployment in long-haul and short-reach communication systems respectively. The current work provides new results in both fields focusing on multi-channel detection in the coherent long-haul domain and on a cost/consumption/performance assessment of neuromorphic photonic processing based on recurrent spectrum slicing in comparison to the state-of-the-art. A thorough analysis of other state-of-the-art techniques in both domains is also provided revealing the merits and shortcomings of recurrent neural networks and neuromorphic photonic processing in high-speed optical communication systems.

关键词： Digital signal processing neural networks optical computing optical fiber communications optical receivers

来源：评论

学校读者我要写书评

暂无评论

optical diffractive neural network imaging through double diffusive mediums

OPTICS CONTINUUM

引用

OPTICS CONTINUUM 2024年第6期3卷 879-892页

作者： Wang, Jialong Chai, Shouyu Gu, Wenting Li, Boyi Liu, Xin Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

The optical diffractive neural network (ODNN) offers the benefits of high-speed parallelism and low energy consumption. This kind of method holds great potential in the task of reconstructing diffusive images. In this work, we capture a double -scattering dataset by designing optical experiments and use it to evaluate the image reconstruction capability of the constructed ODNNs under more complex scattering scenarios. The Pearson Correlation Coefficient, which is used as a quantitative index of the reconstruction performance, shows that the constructed diffractive networks enable to achieve high performance in the direct recovery of double -scattering data, as well as in the recovery task of stitching images based on two different kinds of double -scattering data. Meanwhile, due to the high redundancy of valid information in the speckle patterns of scattering images, even if parts of the information in the speckle patterns are blocked, the constructed diffractive networks can also show high reconstruction performance without retraining. The capability of the proposed ODNN to reconstruct double -scattering images indicates that the optical diffractive network has the potential to bring transformative applications in more complex scattering scenarios. (c) 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Biomedical imaging Imaging systems optical computing optical neural systems Spatial light modulators Speckle patterns

来源：评论

学校读者我要写书评

暂无评论

Towards "smart transceivers" in FPGA-controlled lithium-niobate-on-insulator integrated circuits for edge computing applications [Invited]

引用

optical MATERIALS EXPRESS 2023年第12期13卷 3667-3676页

作者： Bankwitz, J. Rasmus Dijkstra, Jelle Pradip, Ravi McRae, Liam Lomonte, Emma Lenzini, Francesco Pernice, Wolfram H. P. Heidelberg Univ Kirchhoff Inst Phys Heidelberg Germany Ctr Nanotechnol CeNTech Heisenbergstr 11 D-48149 Munster Germany Univ Munster Inst Phys Wilhelm Klemm Str 10 D-48149 Munster Germany

In the realm of advanced computing and signal processing, the need for optimized data processing methodologies is steadily increasing. With the world producing vast quantities of data, computing architectures necessitate to be swifter and more energy efficient. Edge computing architectures such as the NetCast architecture [1] combine the strength of electronic and photonic computing by outsourcing multiply-accumulate operations (MAC) to the optical domain. Herein we demonstrate a hybrid architecture, combining the advantages of FPGA data processing facilitating an ultra-low power electro-optical "smart transceiver" comprised of a lithium-niobate on insulator photonic circuit. The as-demonstrated device combines potential GHz speed data processing, with a power consumption in the order of 6.63 fJ per bit. Our device provides a blueprint of a unit cell for a TFLN smart transceiver alongside a variety of optical computing architectures, such as optical neural networks, as it provides a low power, reconfigurable memory unit.

关键词： Lithium niobate waveguides Machine vision optical computing optical neural systems Quantum computation Signal processing

来源：评论

学校读者我要写书评

暂无评论

Programming the scalable optical learning operator with spatial-spectral optimization

引用

optical FIBER TECHNOLOGY 2024年 87卷

作者： Zhou, Yi Hsieh, Jih-Liang Oguz, Ilker Yildirim, Mustafa Dinc, Niyazi Ulas Gigli, Carlo Wong, Kenneth K. Y. Moser, Christophe Psaltis, Demetri Ecole Polytech Fed Lausanne Lab Appl Photon Devices CH-1015 Lausanne Switzerland Ecole Polytech Fed Lausanne Opt Lab CH-1015 Lausanne Switzerland Univ Hong Kong Dept Elect & Elect Engn Pokfulam Rd Hong Kong Peoples R China

Electronic computers have evolved drastically over the past years with an ever-growing demand for improved performance. However, the transfer of information from memory and high energy consumption have emerged as issues that require solutions. optical techniques are considered promising solutions to these problems with higher speed than their electronic counterparts and with reduced energy consumption. Here, we use the optical reservoir computing framework we have previously described (Scalable optical Learning Operator or SOLO [1]) to program the spatial-spectral output of the light after nonlinear propagation in a multimode fiber. The novelty in the current paper is that the system is programmed through an output sampling scheme, similar to that used in hyperspectral imaging in astronomy. Linear and nonlinear computations are performed by light in the multimode fiber and the high dimensional spatial-spectral information at the fiber output is optically programmed before it reaches the camera. We then used a digital computer to classify the programmed output of the multi-mode fiber using a simple, single layer network. When combining front-end programming and the proposed spatial-spectral programming, we were able to achieve 89.9 % classification accuracy on the dataset consisting of chest X-ray images from COVID-19 patients. At the same time, we obtained a decrease of 99 % in the number of tunable parameters compared to an equivalently performing digital neural network. These results show that the performance of programmed SOLO is comparable with cutting-edge electronic computing platforms, albeit with a much-reduced number of electronic operations.

关键词： optical computing Multimode fiber Nonlinear optics neural networks Spatial-spectral sampling Wavefront shaping

来源：评论

学校读者我要写书评

暂无评论

All-optical control-flow and enhancement of optical neural networks

All-optical control-flow and enhancement of optical neural n...

引用

Conference on Emerging Topics in Artificial Intelligence (ETAI)

作者： Kissner, Michael Ghalanos, George Caruana, Peter Del Bino, Leonardo Akhetonics GmbH Akazienstr 3a D-10823 Berlin Germany

ISBN: (纸本)9781510678972;9781510678965

Current approaches to optical neural networks are only focused on the arithmetic operations, such as matrix vector multiplication and in some cases the activation function. The control flow to enable large matrices, multiple connected layers or methods to increase precision are completely delegated to digital electronics. Here we present our approach to enabling all-optical control flow and precision control to enable full optical AI inference in the future, eliminating the need to jump between the electronic and optical domain for each layer, to increase performance and efficiency.

关键词： Photonics optical computing PIC neural networks AI Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Photonic Neuromorphic Pattern Recognition with a Spiking DFB-SA Laser Subject to Incoherent optical Injection

引用

LASER & PHOTONICS REVIEWS 2025年第1期19卷

作者： Zhang, Yuna Xiang, Shuiying Yu, Chengyang Gao, Shuang Han, Yanan Guo, Xingxing Zhang, Yahui Shi, Yuechun Hao, Yue Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Xidian Univ Sch Microelect State Key Discipline Lab Wide Bandgap Semicond Tec Xian 710071 Peoples R China Yongjiang Lab Ningbo 315202 Peoples R China

Photonic neuromorphic computing is a competitive paradigm to overcome the bottleneck of von Neumann architectures. Incoherent and coherent synaptic networks are two popular schemes realizing photonic weighting functions. Previous works have proved the distributed feedback (DFB) laser with an intracavity saturable absorber (DFB-SA) can behavior like a spiking neuron. However, the compatibility with the incoherent synaptic architecture has not yet been demonstrated. Here the neuron-like dynamics of a DFB-SA laser subject to single-wavelength and multiple-wavelengths incoherent optical injections are experimentally demonstrated. The results show that, for the DFB-SA laser subject to single-wavelength incoherent injection, the neuron-like dynamics including threshold, temporal integration, and refractory period are achieved. Besides, the range of injection wavelength that leads to a successful neuron-like response is identified. For the DFB-SA laser with four-wavelength incoherent optical injection, the neuron-like dynamics can also be achieved. In addition, the effect of wavelength interval is also considered. The logic XOR operation and Iris recognition tasks are successfully implemented. Furthermore, the feasibility of a cascaded system for the DFB-SA lasers with four-wavelengths incoherent optical injection is demonstrated. This work provides a feasible scheme for the system integration of photonic spiking neurons and incoherent synaptic networks. Neuron-like dynamics in a DFB-SA laser with single-wavelength and multiple-wavelengths incoherent optical injections, and successfully implemented logic XOR operations and Iris recognition are experimentally demonstrated. Additionally, The feasibility of a cascaded DFB-SA laser system with four-wavelengths incoherent optical injection is demonstrated. This work offers a viable scheme for integrating photonic spiking neurons and incoherent synaptic networks. image

关键词： DFB-SA laser incoherent architecture multiple wavelengths optical injection photonic neuromorphic computing spiking neural network

来源：评论

学校读者我要写书评

暂无评论

All-optical ultrafast ReLU function for energy-efficient nanophotonic deep learning

引用

NANOPHOTONICS 2023年第5期12卷 847-855页

作者： Li, Gordon H. Y. Sekine, Ryoto Nehra, Rajveer Gray, Robert M. Ledezma, Luis Guo, Qiushi Marandi, Alireza CALTECH Dept Appl Phys Pasadena CA 91125 USA CALTECH Dept Elect Engn Pasadena CA 91125 USA CALTECH Jet Prop Lab Pasadena CA 91125 USA

In recent years, the computational demands of deep learning applications have necessitated the introduction of energy-efficient hardware accelerators. optical neural networks are a promising option;however, thus far they have been largely limited by the lack of energy-efficient nonlinear optical functions. Here, we experimentally demonstrate an all-optical Rectified Linear Unit (ReLU), which is the most widely used nonlinear activation function for deep learning, using a periodically-poled thin-film lithium niobate nanophotonic waveguide and achieve ultra-low energies in the regime of femtojoules per activation with near-instantaneous operation. Our results provide a clear and practical path towards truly all-optical, energy-efficient nanophotonic deep learning.

关键词： deep learning optical computing optical neural networks thin-film lithium niobate

来源：评论

学校读者我要写书评

暂无评论

Photonic Hopfield neural network for the Ising problem

引用

OPTICS EXPRESS 2023年第13期31卷 21340-21350页

作者： Fan, Zeyang Lin, Junmin Dai, Jian Zhang, Tian Xu, Kun Beijing Univ Posts & Telecommun State Key Lab Informat Photon & Opt Commun Beijing 100876 Peoples R China

The Ising problem, a vital combinatorial optimization problem in various fields, is hard to solve by traditional Von Neumann computing architecture on a large scale. Thus, lots of application-specific physical architectures are reported, including quantum-based, electronics based, and optical-based platforms. A Hopfield neural network combined with a simulated annealing algorithm is considered one of the effective approaches but is still limited by large resource consumption. Here, we propose to accelerate the Hopfield network on a photonic integrated circuit composed of the arrays of Mach-Zehnder interferometer. Our proposed Photonic Hopfield neural Network (PHNN), utilizing the massively parallel operations and integrated circuit with ultrafast iteration rate, converges to a stable ground state solution with high probability. The average success probabilities for the MaxCut problem with a problem size of 100 and the Spin-glass problem with a problem size of 60 can both reach more than 80%. Moreover, our proposed architecture is inherently robust to the noise induced by the imperfect characteristics of components on chip.

关键词： Analog to digital converters neural networks optical computing architecture optical devices optical directional couplers Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

optical neural networks with Tensor Compression and Photonic Memory

Optical Neural Networks with Tensor Compression and Photonic...

引用

optical Fiber Communications Conference and Exhibition (OFC)

作者： Xiao, Xian Cheung, Stanley Tossoun, Bassem Van Vaerenbergh, Thomas Kurczveil, Geza Beausoleil, Raymond G. Hewlett Packard Enterprise Hewlett Packard Labs 820 N McCarthy Blvd Milpitas CA 95305 USA

This paper introduces our recent efforts on scalable, energy-efficient, and low-latency tensorized optical neural networks, including design considerations, options for wavelength-parallel photonic tensor cores, and p... 详细信息

ISBN: (纸本)9798350377583

关键词： Avalanche photodiodes neural networks optical computing optical network architecture optical neural systems Quantum dot lasers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：