检索结果-内蒙古大学图书馆

Photonic Multiply-Accumulate Operations for neural networks

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 2020年第1期26卷

作者： Nahmias, Mitchell A. de Lima, Thomas Ferreira Tait, Alexander N. Peng, Hsuan-Tung Shastri, Bhavin J. Prucnal, Paul R. Princeton Univ Dept Elect Engn Princeton NJ 08544 USA Queens Univ Dept Phys Engn Phys & Astron Kingston ON K7L 3N6 Canada

It has long been known that photonic communication can alleviate the data movement bottlenecks that plague conventional microelectronic processors. More recently, there has also been interest in its capabilities to implement low precision linear operations, such as matrix multiplications, fast and efficiently. We characterize the performance of photonic and electronic hardware underlying neural network models using multiply-accumulate operations. First, we investigate the limits of analog electronic crossbar arrays and on-chip photonic linear computing systems. Photonic processors are shown to have advantages in the limit of large processor sizes (>100 mu m), large vector sizes (N > 500), and low noise precision (<= 4 bits). We discuss several proposed tunable photonic MAC systems, and provide a concrete comparison between deep learning and photonic hardware using several empiricallyvalidated device and system models. We show significant potential improvements over digital electronics in energy (>10(2)), speed (>10(3)), and compute density (>10(2)).

关键词： Photonics neural networks Program processors Computational modeling Deep learning Training Metals Artificial intelligence neural networks analog computers analog processing circuits optical computing

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

arXiv 2020年

作者： Zhou, Tiankuang Lin, Xing Wu, Jiamin Chen, Yitong Xie, Hao Li, Yipeng Fan, Jintao Wu, Huaqiang Fang, Lu Dai, Qionghai Department of Automation Tsinghua University Beijing100084 China Institute for Brain and Cognitive Science Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Innovation Center for Future Chips Tsinghua University Beijing100084 China Graduate School at Shenzhen Tsinghua University Shenzhen518055 China Department of Electronic Engineering Tsinghua University Beijing100084 China Institute of Microelectronics Tsinghua University Beijing100084 China

Application-specific optical processors have been considered disruptive technologies for modern computing that can fundamentally accelerate the development of artificial intelligence (AI) by offering substantially improved computing performance. Recent advancements in optical neural network architectures for neural information processing have been applied to perform various machine learning tasks. However, the existing architectures have limited complexity and performance;and each of them requires its own dedicated design that cannot be reconfigured to switch between different neural network models for different applications after deployment. Here, we propose an optoelectronic reconfigurable computing paradigm by constructing a diffractive processing unit (DPU) that can efficiently support different neural networks and achieve a high model complexity with millions of neurons. It allocates almost all of its computational operations optically and achieves extremely high speed of data modulation and large-scale network parameter updating by dynamically programming optical modulators and photodetectors. We demonstrated the reconfiguration of the DPU to implement various diffractive feedforward and recurrent neural networks and developed a novel adaptive training approach to circumvent the system imperfections. We applied the trained networks for high-speed classifying of handwritten digit images and human action videos over benchmark datasets, and the experimental results revealed a comparable classification accuracy to the electronic computing approaches. Furthermore, our prototype system built with off-the-shelf optoelectronic components surpasses the performance of state-of-the-art graphics processing units (GPUs) by several times on computing speed and more than an order of magnitude on system energy efficiency. We believe the proposed reconfigurable DPU is a remarkable step towards high-performance neuromorphic optoelectronic computing processors that can achieve r

关键词： network architecture

来源：评论

学校读者我要写书评

暂无评论

Devon: Deformable Volume network for Learning optical Flow

Devon: Deformable Volume Network for Learning Optical Flow

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yao Lu Jack Valmadre Heng Wang Juho Kannala Mehrtash Harandi Philip H. S. Torr Data61 ANU ACRV

ISBN: (数字)9781728165530

ISBN: (纸本)9781728165547

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two problems with the approach. First, the multi-resolution estimation of optical flow fails in situations where small objects move fast. Second, warping creates artifacts when occlusion or dis-occlusion happens. In this paper, we propose a new neural network module, Deformable Cost Volume, which alleviates the two problems. Based on this module, we designed the Deformable Volume network (Devon) which can estimate multi-scale optical flow in a single high resolution. Experiments show Devon is more suitable in handling small objects moving fast and achieves comparable results to the state-of-the-art methods in public benchmarks.

关键词： optical imaging optical computing optical distortion neural networks optical fiber networks optical propagation Estimation

来源：评论

学校读者我要写书评

暂无评论

深度学习光流计算技术研究进展

引用

电子学报 2020年第9期48卷 1841-1849页

作者：张聪炫周仲凯陈震葛利跃黎明江少锋陈昊南昌航空大学无损检测技术教育部重点实验室江西南昌330063 中国科学院自动化研究所北京100190

图像序列光流计算是图像处理与计算机视觉等领域的重要研究方向.随着深度学习技术的快速发展,以卷积神经网络为代表的深度学习理论与方法成为光流计算技术研究的热点.本文主要对深度学习光流计算技术研究进行综述,首先介绍了有监督学习... 详细信息

图像序列光流计算是图像处理与计算机视觉等领域的重要研究方向.随着深度学习技术的快速发展,以卷积神经网络为代表的深度学习理论与方法成为光流计算技术研究的热点.本文主要对深度学习光流计算技术研究进行综述,首先介绍了有监督学习、无监督学习和半监督学习的光流计算网络模型与训练策略,然后重点阐述并分析了不同网络模型优化方法.针对光流计算模型的评估问题,分别介绍了Middlebury、MPI-Sintel和KITTI等数据库及评价基准,并对不同类型深度学习和传统变分光流模型进行对比与分析.最后,总结了深度学习光流计算技术在模型复杂度与泛化性、光流估计鲁棒性、小样本训练准确性等方面的关键技术问题,并指出了可能的解决方案与研究思路.

关键词：光流计算深度学习卷积神经网络训练策略优化方法评价基准

来源：评论

学校读者我要写书评

暂无评论

Recurrent residual U-Net for medical image segmentation

引用

JOURNAL OF MEDICAL IMAGING 2019年第1期6卷 014006页

作者： Alom, Md Zahangir Yakopcic, Chris Hasan, Mahmudul Taha, Tarek M. Asari, Vijayan K. Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA Comsat Labs Washington DC USA

Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep architectures. Second, feature accumulation with recurrent residual convolutional layers ensures better feature representation for segmentation tasks. Third, it allows us to design better U-Net architectures with the same number of network parameters with better performance for medical image segmentation. The proposed models are tested on three benchmark datasets, such as blood vessel segmentation in retinal images, skin cancer segmentation, and lung lesion segmentation. The experimental results show superior performance on segmentation tasks compared to equivalent models, including a variant of a fully connected convolutional neural network called SegNet, U-Net, and residual U-Net. (C) 2019 Society of Photo-optical Instrumentation Engineers (SPIE)

关键词： medical imaging semantic segmentation convolutional neural networks U-Net residual U-Net recurrent U-Net recurrent residual U-Net

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Short-Term Quantitative Precipitation Forecasting 2020

A Deep Learning Approach to Short-Term Quantitative Precipit...

引用

Proceedings of the 10th International Conference on Climate Informatics

作者： Nishant Yadav Auroop R. Ganguly Northeastern University US

ISBN: (纸本)9781450388481

Short-term, spatially distributed quantitative precipitation forecasting (SD-QPF), or ‘precipitation nowcasting’, is important for hydrological and water resources applications, such as flash flood warning systems and operations of dams and reservoirs. The state-of-the-art methods in SD-QPF include radar extrapolations, numerical weather prediction (NWP) models, and hybrid methods that combine the two. Despite the diversity of methods that have been used, SD-QPF remains difficult: even sophisticated methods may not be able to consistently outperform relatively simple baselines such as Persistence. Methods in Deep Learning (DL) have demonstrated significant and often unexpected improvements across a wide variety of domains ranging from image and video processing to machine translation and speech recognition. Emerging research has suggested that that DL may improve point predictions in the context of very short-term - 0-2 hours - distributed QPF (VSD-QPF) by taking advantage of growing data from in-situ weather sensors as well as remote sensors such as radar and satellites, along with advances in computing. Here we examine the hypothesis that DL can improve VSD-QPF, specifically point predictions, based on observed hourly precipitation data over the contiguous United States, by leveraging a Convolutional Long Short-Term Memory (LSTM) recurrent neural network for 1-hour precipitation nowcasting. We find the DL approach performs better than the baseline method of Persistence and a state-of-the-art method using optical Flow.

关键词： optical flow precipitation forecasting deep learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep models for Predicting Affective Responses Evoked by Movies 17

Multimodal Deep Models for Predicting Affective Responses Ev...

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Ha Thi Phuong Thao Herremans, Dorien Roig, Gemma Singapore Univ Technol & Design 8 Somapah Rd Singapore 487372 Singapore

ISBN: (纸本)9781728150239

The goal of this study is to develop and analyze multimodal models for predicting experienced affective responses of viewers watching movie clips. We develop hybrid multimodal prediction models based on both the video and audio of the clips. For the video content, we hypothesize that both image content and motion are crucial features for evoked emotion prediction. To capture such information, we extract features from RGB frames and optical flow using pre-trained neural networks. For the audio model, we compute an enhanced set of low-level descriptors including intensity, loudness, cepstrum, linear predictor coefficients, pitch and voice quality. Both visual and audio features are then concatenated to create audio-visual features, which are used to predict the evoked emotion. To classify the movie clips into the corresponding affective response categories, we propose two approaches based on deep neural network models. The first one is based on fully connected layers without memory on the time component, the second incorporates the sequential dependency with a long short-term memory recurrent neural network (LSTM). We perform a thorough analysis of the importance of each feature set. Our experiments reveal that in our set-up, predicting emotions at each time step independently gives slightly better accuracy performance than with the LSTM. Interestingly, we also observe that the optical flow is more informative than the RGB in videos, and overall, models using audio features are more accurate than those based on video features when making the final prediction of evoked emotions.

关键词： Affective computing Emotion prediction Movie analysis Multimodal approach neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent high-performance computing for big data processing in fiber optical measuring networks 5

Intelligent high-performance computing for big data processi...

引用

5th International Conference on Information Technologies and High-Performance computing, ITHPC 2019

作者： Zakasovskaya, Elena V. Tarasov, Valentin S. Denisova, Nadezhda I. Vladivostok State University of Economics and Service Vladivostok Russia Far Eastern Federal University Vladivostok Russia Saint Petersburg University St Petersburg Russia

The paper deals with the problem of reconstructing the parameters of physical fields using distributed information and measurement systems for cases of incomplete laying of measurement lines. High-performance computing is typically used for solving advanced problems and performing research activities through computer modeling. The rise of Big Data has changed the entire perspective of data and data handling. Ever growing analytical needs for Big Data can be satisfied with extremely high-performance computing models. A new combined algorithm is presented, which is concluded in the "optimization of the geometry" of the measuring network with a view to further applying the complex of neural networks. The possibility of choosing and using the appropriate neural network from a complex of several pre-trained. © 2019 CEUR-WS. All rights reserved.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Training of mixed-signal optical convolutional neural network with reduced quantization level

arXiv

引用

arXiv 2020年

作者： Ulseth, Joseph Zhu, Zheyuan Li, Guifang Pang, Shuo CREOL College of Optics and Photonics University of Central Florida 4304 Scorpius St OrlandoFL32816 United States

Mixed-signal artificial neural networks (ANNs) that employ analog matrix-multiplication accelerators can achieve higher speed and improved power efficiency. Though analog computing is known to be susceptible to noise and device imperfections, various analog computing paradigms have been considered as promising solutions to address the growing computing demand in machine learning applications, thanks to the robustness of ANNs. This robustness has been explored in low-precision, fixed-point ANN models, which have proven successful on compressing ANN model size on digital computers. However, these promising results and network training algorithms cannot be easily migrated to analog accelerators. The reason is that digital computers typically carry intermediate results with higher bit width, though the inputs and weights of each ANN layers are of low bit width;while the analog intermediate results have low precision, analogous to digital signals with a reduced quantization level. Here we report a training method for mixed-signal ANN with two types of errors in its analog signals, random noise, and deterministic errors (distortions). The results showed that mixed-signal ANNs trained with our proposed method can achieve an equivalent classification accuracy with noise level up to 50% of the ideal quantization step size. We have demonstrated this training method on a mixed-signal optical convolutional neural network based on diffractive optics. Copyright © 2020, The Authors. All rights reserved.

关键词： Digital computers

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Integration of Rich Features for Video-Based Person Re-Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2019年第12期29卷 3646-3659页

作者： Liu, Zheng Wang, Yunhong Li, Annan Beihang Univ State Key Lab Virtual Real Technol & Syst Sch Engn & Comp Sci Beijing 100083 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp Beijing 100083 Peoples R China

Person re-identification (ReID) aims to associate the identity of pedestrians captured by cameras across non-overlapped areas. Video-based ReID plays an important role in intelligent video surveillance systems and has attracted growing attention in recent years. In this paper, we propose an end-to-end video-based ReID framework based on the convolutional neural network (CNN) for efficient spatio-temporal modeling and enhanced similarity measuring. Specifically, we build our descriptor of sequences by basic mathematical calculations on the semantic mid-level image features, which avoids the time consuming computations and the loss of spatial correlations. We further hierarchically extract image features from multiple intermediate CNN stages to build multi-level sequence descriptors. For a descriptor at one stage, we design an effective auxiliary pairwise loss which is jointly optimized with a triplet loss. To integrate hierarchical representation, we propose an intuitive yet effective summation-based similarity integration scheme to match identities more accurately. Furthermore, we extend our framework by a multi-model ensemble strategy, which effectively assembles three popular CNN models to represent walking sequences more comprehensively and improve the performance. Extensive experiments on three video-based ReID datasets show that the proposed framework outperforms the state-of-the-art methods.

关键词： Feature extraction Legged locomotion Semantics optical computing optical imaging Visualization Recurrent neural networks Person re-identification spatio-temporal aggregation similarity measuring multi-model ensemble

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：