检索结果-内蒙古大学图书馆

Mixed precision quantization of silicon optical neural network chip

OPTICS COMMUNICATIONS 2025年 574卷

作者： Zhang, Ye Wang, Ruiting Zhang, Yejin Pan, Jiaoqing Beijing Informat Sci & Technol Univ Beijing 100192 Peoples R China Chinese Acad Sci Key Lab Semicond Mat Sci Inst Semicond Beijing 100083 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Beijing 100049 Peoples R China

In recent years, the field of neural network research has witnessed remarkable advancements in various domains. One of the emerging approaches is the integration of photonic computing, which leverages the unique properties of light for ultra-fast information processing. In this article, we establish a mixed precision quantization model to silicon-based optical neural networks and evaluates their performance on the MNIST and Fashion-MNIST datasets. Through a genetic algorithm- based optimization process, we achieve significant parameter compression while maintaining competitive accuracy. Our findings demonstrate that with an average quantization bitwidth of 4.5 bits on the MNIST dataset, we achieve an impressive 85.94% reduction in parameter size compared to traditional 32-bit networks, with only a marginal accuracy drop of 0.65%. Similarly, on the Fashion-MNIST dataset, we achieve an average quantization bitwidth of 5.67 bits, resulting in an 82.28% reduction in parameter size with a slight accuracy drop of 0.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

optical multi-task learning using multi-wavelength diffractive deep neural networks

引用

NANOPHOTONICS 2023年第5期12卷 893-903页

作者： Duan, Zhengyang Chen, Hang Lin, Xing Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China

Photonic neural networks are brain-inspired information processing technology using photons instead of electrons to perform artificial intelligence (AI) tasks. However, existing architectures are designed for a single task but fail to multiplex different tasks in parallel within a single monolithic system due to the task competition that deteriorates the model performance. This paper proposes a novel optical multitask learning system by designing multiwavelength diffractive deep neural networks (D(2)NNs) with the joint optimization method. By encoding multitask inputs into multiwavelength channels, the system can increase the computing throughput and significantly alleviate the competition to perform multiple tasks in parallel with high accuracy. We design the two-task and four-task D(2)NNs with two and four spectral channels, respectively, for classifying different inputs from MNIST, FMNIST, KMNIST, and EMNIST databases. The numerical evaluations demonstrate that, under the same network size, multiwavelength D(2)NNs achieve significantly higher classification accuracies for multitask learning than single-wavelength D(2)NNs. Furthermore, by increasing the network size, the multiwavelength D(2)NNs for simultaneously performing multiple tasks achieve comparable classification accuracies with respect to the individual training of multiple single-wavelength D(2)NNs to perform tasks separately. Our work paves the way for developing the wavelength-division multiplexing technology to achieve high-throughput neuromorphic photonic computing and more general AI systems to perform multiple tasks in parallel.

关键词： diffractive deep neural networks multi-wavelength photonic neural networks optical multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Optoelectronic nonlinear Softmax operator based on diffractive neural networks

引用

OPTICS EXPRESS 2024年第15期32卷 26458-26469页

作者： Zhan, Ziyu Wang, Hao Liu, Qiang Fu, Xing Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China State Key Lab Precis Space time Informat Sensing T Beijing 100084 Peoples R China Tsinghua Univ Key Lab Photon Control Technol Minist Educ Beijing 100084 Peoples R China

Softmax, , a pervasive nonlinear operation, plays a pivotal role in numerous statistics and deep learning (DL) models such as ChatGPT. To compute it is expensive especially for at-scale models. Several software and hardware speed-up strategies are proposed but still suffer from low efficiency, poor scalability. Here we propose a photonic-computing solution including massive programmable neurons that is capable to execute such operation in an accurate, computation-efficient, robust and scalable manner. Experimental results show our diffraction- based computing system exhibits salient generalization ability in diverse artificial and real-world tasks (mean square error < 10(-5)). We further analyze its performances against several realistic restricted factors. Such flexible system not only contributes to optimizing Softmax operation mechanism but may provide an inspiration of manufacturing a plug-and-play module for general optoelectronic accelerators.

关键词： Deep learning Machine vision neural networks optical computing Probability theory Signal processing

来源：评论

学校读者我要写书评

暂无评论

Self-Configurable Stabilized Real-Time Detection Learning for Autonomous Driving Applications

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第1期24卷 885-890页

作者： Yun, Won Joon Park, Soohyun Kim, Joongheon Mohaisen, David Korea Univ Sch Elect Engn Seoul 02841 South Korea Univ Cent Florida Dept Comp Sci Orlando FL 32816 USA

Guaranteeing real-time and accurate object detection simultaneously is paramount in autonomous driving environments. However, the existing object detection neural network systems are characterized by a tradeoff between computation time and accuracy, making it essential to optimize such a tradeoff. Fortunately, in many autonomous driving environments, images come in a continuous form, providing an opportunity to use optical flow. In this paper, we improve the performance of an object detection neural network utilizing optical flow estimation. In addition, we propose a Lyapunov optimization framework for time-average performance maximization subject to stability. It adaptively determines whether to use optical flow to suit the dynamic vehicle environment, thereby ensuring the vehicle's queue stability and the time-average maximum performance simultaneously. To verify the key ideas, we conduct numerical experiments with various object detection neural networks and optical flow estimation networks. In addition, we demonstrate the self-configurable stabilized detection with YOLOv3-tiny and FlowNet2-S, which are the real-time object detection network and an optical flow estimation network, respectively. In the demonstration, our proposed framework improves the accuracy by 3.02%, the number of detected objects by 59.6%, and the queue stability for computing capabilities.

关键词： optical imaging Object detection optical computing Real-time systems Autonomous vehicles Estimation optical fiber networks Autonomous driving real-time object detection computer vision Lyapunov optimization

来源：评论

学校读者我要写书评

暂无评论

Accelerated Information Processing Based on Deep Photonic Time-Delay Reservoir computing

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2024年第24期42卷 8739-8747页

作者： Zhang, Jiahao Zhang, Lu Pang, Xiaodan Ozolins, Oskars Yu, Xianbin Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China KTH Royal Inst Technol Appl Phys Dept S-10691 Stockholm Sweden RISE Res Inst Sweden Networks Unit S-16440 Kista Sweden Riga Tech Univ Inst Photon Elect & Telecommun LV-1048 Riga Latvia

Photonic time-delay reservoir computing (TDRC) is an optical neural network structure known for its simple hardware implementation. However, this simplicity reduces information processing speed due to its sequential time multiplexing mechanism, such as the masking operation in practical experiments. To address this, we employ a deep photonic TDRC structure to enhance reservoir dynamics, effectively reducing the mask size to accelerate processing while maintaining high performance. An extended state matrix is proposed to leverage the enriched dynamics without additional hardware costs, combining different nonlinear intensities and memory lengths to augment node states without physically expanding the reservoir. Experimentally validated in a speech recognition task, our approach accelerates processing by 10 times with only a 2.4% decrease in recognition accuracy, compared to a 13.1% accuracy deterioration in the conventional scheme, indicating significant acceleration in TDRC information processing while maintaining performance.

关键词： Reservoirs Task analysis Hardware Information processing Photonics neural networks Multiplexing Computation acceleration optical neural network reservoir computing speech recognition

来源：评论

学校读者我要写书评

暂无评论

Training optronic convolutional neural networks on an optical system through backpropagation algorithms

引用

OPTICS EXPRESS 2022年第11期30卷 19416-19440页

作者： Gu, Ziyu Huang, Zicheng Gao, Yesheng Liu, Xingzhao Shanghai Jiao Tong Univ State Key Lab Adv Opt Commun Syst & Networks 800 Dongchuan Rd Shanghai 200240 Peoples R China

The development of optical neural networks greatly slows the urgent demand of searching for fast computing approaches to solve big data processing. However, most optical neural networks following electronic training and optical inferencing do not really take full advantage of optical computing to reduce computational burden. Take the extensively used optronic convolutional neural networks (OPCNN) as an example, the convolutional operations still require vast computational operations in training stages on the computer. To address this issue, this study proposes the in-situ training algorithm to train the networks directly in optics. We derive the backpropagation algorithms of OPCNN hence the complicated gradient calculation in backward propagating processes can be obtained through optical computing. Both forward propagation and backward propagation are all executed on the same optical system. Furthermore, we successfully realize the introduction of optical nonlinearity in networks through utilizing photorefractive crystal SBN:60 and we also derive the corresponding backpropagation algorithm. The numerical simulation results of classification performance on several datasets validates the feasibility of the proposed algorithms. Through in-situ training, the reduction in performance resulting from the inconsistency of the plantform between training and inferencing stages can be eliminated completely. For example, we demonstrate that by using the optical training approach, OPCNN is capable of gaining a strong robustness under several misalignmed situations, which enhances the practicability of OPCNN and greatly expands its application range. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： neural networks Numerical simulation optical components optical computing optical networks optical neural systems

来源：评论

学校读者我要写书评

暂无评论

Confluence of Photonics and Artificial Intelligence

引用

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 2025年第3期31卷

作者： Chen, Young-Kai Coherent Corp Santa Clara CA 95054 USA

Over the past decades, significant advances have been made in the fields of photonic technologies, artificial intelligence, and machine learning techniques. Recent AI progress in language models, perception and self-learning capability has had a significant impact on a wide range of communities. The new photonics enhances AI with faster data processing, reduced energy consumption, and improved interconnects, enabling more efficient and powerful AI systems. In this paper, we will highlight the synchroneity of these advances from performance enhancement of AI processing by photonics and advanced photonics with AI processing, leading to new photonic neural networks for future photonic AI processors.

关键词： optical switches Artificial intelligence High-speed optical techniques optical fiber communication optical distortion optical interconnections Photonics optical amplifiers optical polarization Training optical interconnects optical switching photonic inverse design photonic processing photonic neural network photonic computing artificial intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Fiber Nonlinearity Compensation Using Nonlinear Equalizer Based on Complex-Valued Reservoir computing

引用

IEICE TRANSACTIONS ON COMMUNICATIONS 2025年第3期E108B卷 250-259页

作者： Ikuta, Kai Ito, Yuta Sakamoto, Takahide Yamamoto, Naokatsu Nakamura, Moriya Meiji Univ Kawasaki 214 8571 Japan Tokyo Metropolitan Univ Hino 191 0065 Japan Natl Inst Informat & Commun Technol Koganei 1848795 Japan

We investigated the performance of a nonlinear equalizer based on complex-valued reservoir computing (CVRC) for compensation of nonlinear waveform distortion caused by fiber nonlinearity in optical fiber communication systems. Reservoir computing (RC) is a kind of neuromorphic signal-processing algorithm. One important advantage of RC is the high-speed training capability compared to feedforward artificial neural networks (ANNs) with multiple (three or more) layers. CVRC can lower the computational complexity and directly deal with the complex amplitude of the IQ-modulated optical signals. We analyzed the impact of various parameters in CVRC on the equalization performance. The parameters include the number of reservoir units, the spectral radius, the timing of the training signal, and sparse connectivity. By optimizing these parameters, we achieved efficient operation of the CVRC-based nonlinear equalizers, making them applicable to various optical transmission distances. A comparative performance evaluation between CVRC and conventional real- valued RC (RVRC) was conducted through numerical simulations and experiments. We clarified that the CVRC-based nonlinear equalizer requires only about half the number of reservoir units compared to the RVRC-based nonlinear equalizer and reduces the computational complexity to approximately one-quarter.

关键词： digital coherent transmission optical nonlinearity mitigation nonlinear equalization reservoir computing

来源：评论

学校读者我要写书评

暂无评论

Photonic neural networks Based on Integrated Silicon Microresonators

INTELLIGENT COMPUTING

引用

INTELLIGENT computing 2024年 3卷

作者： Biasi, Stefano Donati, Giovanni Lugnan, Alessio Mancinelli, Mattia Staffoli, Emiliano Pavesi, Lorenzo Univ Trento Dept Phys Nanosci Lab Trento Italy

Recent progress in artificial intelligence (AI) has boosted the computational possibilities in fields in which standard computers are not able to perform adequately. The AI paradigm is to emulate human intelligence and therefore breaks the familiar architecture on which digital computers are based. In particular, neuromorphic computing, artificial neural networks (ANNs), and deep learning models mimic how the brain computes. There are many applications for large networks of interconnected neurons whose synapses are individually strengthened or weakened during the learning phase. In this respect, photonics is a suitable platform for implementing ANN hardware owing to its speed, low power dissipation, and multi-wavelength opportunities. One photonic device that could serve as an optical neuron is the optical microring resonator. Indeed, microring resonators exhibit a nonlinear response and the capability for optical energy storage, which can be used to implement fading memory. In addition, their characteristic resonant behavior makes them extremely sensitive to input wavelengths, which promotes wavelength division multiplexing (WDM) applications and enables their use as WDM-based synapses (weight banks) in the linear regime. Remarkably, using silicon photonics, photonic integrated circuits can be fabricated in volume and with integrated electronics onboard. For these reasons, here, we describe the physics of silicon microring resonators and arrays of microring resonators for application in neuromorphic computing. We describe different types of ANNs, from feedforward networks to photonic extreme learning machines, and reservoir computing. In addition, we discuss hybrid systems in which silicon microresonators are coupled with other active materials. This review introduces the basics and discusses the most recent developments in the field.

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Effects of cavity nonlinearities and linear losses on silicon microring-based reservoir computing

引用

OPTICS EXPRESS 2024年第2期32卷 2039-2057页

作者： Castro, Bernard J. Giron Peucheret, Christophe Zibar, Darko Da Ros, Francesco Tech Univ Denmark DTU Dept Elect & Photon Engn 343 Orsteds Plads DK-2800 Lyngby Denmark Univ Rennes CNRS UMR6082 FOTON F-22305 Lannion France

Microring resonators (MRRs) are promising devices for time-delay photonic reservoir computing, but the impact of the different physical effects taking place in the MRRs on the reservoir computing performance is yet to be fully understood. We numerically analyze the impact of linear losses as well as thermo-optic and free-carrier effects relaxation times on the prediction error of the time-series task NARMA-10. We demonstrate the existence of three regions, defined by the input power and the frequency detuning between the optical source and the microring resonance, that reveal the cavity transition from linear to nonlinear regimes. One of these regions offers very low error in time-series prediction under relatively low input power and number of nodes while the other regions either lack nonlinearity or become unstable. This study provides insight into the design of the MRR and the optimization of its physical properties for improving the prediction performance of time-delay reservoir computing.

关键词： Coupled mode theory Integrated photonics Machine learning neural networks optical computing Semiconductor optical amplifiers

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：