检索结果-内蒙古大学图书馆

26th IEEE International Conference on parallel and distributed Systems (IEEE ICPADS)

作者： Lei, Yutian Deng, Qingyong Long, Saiqin Liu, Shaohui Oh, Sangyoon Xiangtan Univ Sch Comp Sci Key Lab Hunan Prov Internet Things & Informat Sec Sci & Technol Parallel & Distributed Proc Lab Xiangtan Peoples R China PengCheng Lab Artificial Intelligence Ctr Shenzhen Peoples R China Ajou Univ Suwon South Korea

ISBN: (纸本)9781728190747

Convolutional neural networks (CNNs) have been widely used in various complicated problems, such as image classification, objection detection, semantic segmentation. To meet diversified CNN structures, the deep learning processing unit (DPU) is designed as a general accelerator on field programmable gate array (FPGA) to support various CNN layers, such as convolution, pooling, activation, etc. However, low DPU utilization and schedule efficiency appear when DPU used to multitask application completed by CNN models. In this paper, an effective design including multi-core with different size (MCDS) and DPU Plus is proposed to improve the efficiency of DPUs usage from the two dimensions of time and space. Through increasing the number of DPU cores on an FPGA and the utilization of single DPU core, the design of MCDS can effectively improve the overall throughput with restricted on-chip resources. Furthermore, the design of DPU Plus is proposed to improve the schedule efficiency of DPUs through simultaneously implementing DPU with other significant auxiliary modules of the application system on the same FPGA. Finally, a color space conversion module is implemented cooperate to the DPU cores to testify its performance, and the experimen shows that compared with running on the the CPU completely, it achieves16.2x acceleration, and increases the throughput of the entire system by 3.0x.

关键词： Deep learning processor unit (DPU) convolutional neural network (CNN) field programmable gate array (FPGA) efficiency

来源：评论

学校读者我要写书评

暂无评论

Bi-graph attention network for aspect category sentiment classification

引用

KNOWLEDGE-BASED SYSTEMS 2022年 258卷

作者： Shan, Yongxue Che, Chao Wei, Xiaopeng Wang, Xiaodong Zhu, Yongjun Jin, Bo Dalian Univ Minist Educ Key Lab Adv Design & Intelligent Comp Dalian Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha Peoples R China Yonsei Univ Dept Lib & Informat Sci Seoul South Korea Dalian Univ Technol Sch Innovat & Entrepreneurship Dalian Peoples R China

Aspect category sentiment classification (ACSC) aims to determine the sentiment polarities of sentences under given aspect categories, which can be used to infer finer-grained information in text sequences. It is widely used in consumer services, healthcare, and elections. Most models ignore the interaction of global sequence context and syntactic structure information in sentences and fail to fully learn the rich relations between word nodes related to specific aspect categories. To tackle these problems, this paper introduces a bi-graph attention network (BiGAT) for ACSC, which constructs two graphs to describe the sequential context information and syntactic structure information in sentences. It utilizes the graph attention network to aggregate neighbor information from each node within a single graph and uses biaffine modules to coordinate heterogeneous information between the sequential-and syntactic-based graphs. The model uses the aspect-specific mask operation and retrieval-based attention mechanism to reduce the effect of noise created by useless information in sentences. Experimental results on the SemEval 2015, SemEval 2016, and MAMS datasets show that BiGAT outperforms other state-of-the-art ACSC models.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Aspect category sentiment classification Graph attention network Biaffine module Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

HPDL: Towards a General Framework for High-performance distributed Deep Learning 39

HPDL: Towards a General Framework for High-performance Distr...

引用

39th IEEE International Conference on distributed Computing Systems (ICDCS)

作者： Li, Dongsheng Lai, Zhiquan Ge, Keshi Zhang, Yiming Zhang, Zhaoning Sun, Tao Wang, Qinglin Wang, Huaimin Natl Univ Def Technol Sch Comp Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9781728125190

With growing scale of the data volume and neural network size, we have come into the era of distributed deep learning. High-performance training and inference on distributed computing systems has been attracting increasing research attention in both academia and industry. Meanwhile, diversity of existing machine learning frameworks (e.g. TensorFlow, Pytorch and MXNet) and the explosion of deep learning hardwares (e.g. CPUs, GPUs, FPGAs and ASICs) bring more challenges for users to leverage new deep learning technologies and accelerating capability of hardware devices. We firstly search around the state-of-the-art work in the area which open our mind to take a vision upon the future deep learning framework. Then, we propose HPDL, a general framework for high-performance distributed deep learning which is compatible with existing frameworks and adaptive to various hardware architectures. At last, we discuss and foresee the key technologies fulfilling high-performance and large-scale deep learning, including optimization algorithm, hybrid communication mechanism, model parallelization, resource scheduling and single-node execution optimization.

关键词： deep learning distributed algorithm high-performance framework

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stock Price Trend Prediction via a Time-Sensitive Data Augmentation Method

引用

COMPLEXITY 2020年第1期2020卷

作者： Teng, Xiao Wang, Tuo Zhang, Xiang Lan, Long Luo, Zhigang Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Changsha Peoples R China Natl Univ Def Technol Coll Comp Changsha Peoples R China Natl Univ Def Technol Inst Quantum Informat Changsha Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha Peoples R China

Stock trend prediction refers to predicting future price trend of stocks for seeking profit maximum of stock investment. Although it has aroused broad attention in stock markets, it is still a tough task not only because the stock markets are complex and easily volatile but also because real short-term stock data is so limited that existing stock prediction models could be far from perfect, especially for deep neural networks. As a kind of time-series data, the underlying patterns of stock data are easily influenced by any tiny noises. Thus, how to augment limited stock price data is an open problem in stock trend prediction, since most data augmentation schemes adopted in image processing cannot be brutally used here. To this end, we devise a simple yet effective time-sensitive data augmentation method for stock trend prediction. To be specific, we augment data by corrupting high-frequency patterns of original stock price data as well as preserving low-frequency ones in the frame of wavelet transformation. The proposed method is motivated by the fact that low-frequency patterns without noisy corruptions do not hurt the true patterns of stock price data. Besides, a transformation technique is proposed to recognize the importance of the patterns at varied time points, that is, the information is time-sensitive. A series of experiments carried out on a real stock price dataset including 50 corporation stocks verify the efficacy of our data augmentation method.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE ACCESS 2020年 8卷 81394-81411页

作者： Shen, Xingyu Zhang, Xiang Lan, Long Liao, Qing Luo, Zhigang Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Peoples R China Harbin Inst Technol Shenzhen Dept Comp Sci & Technol Shenzhen 518055 Peoples R China

Non-negative matrix factorization (NMF) known as learnt parts-based representation has become a data analysis tool for clustering tasks. It provides an alternative learning paradigm to cope with non-negative data clustering. In this paradigm, concept factorization (CF) and symmetric non-negative factorization (SymNMF) are two typically important representative models. In general, they have distinct behaviors: in CF, each cluster is modeled as a linear combination of samples, and vice versa, i.e., sample reconstruction, while SymNMF built on pair-wise sample similarity measure, is to preserve similarity of samples in a low-dimensional subspace, namely similarity reconstruction. In this paper, we propose a similarity-based concept factorization (SCF) as a synthesis of the two behaviors. This design can be formulated as: the similarity of reconstructed samples by CF is close to that of original samples. To optimize it, we develop an optimization algorithm which leverages the alternating direction of multipliers (ADMM) method to solve each sub-problem of SCF. Besides, we take a further step to consider the robust issue of similarity reconstruction and explore a robust SCF model (RSCF), which penalizes the hardest pair-wise similarity reconstruction via l(infinity). Thus, RSCF enjoys similarity preservation, robustness to similarity perturbation, and ability of reconstructing samples. Extensive experiments validate such properties and show that the proposed SCF and RSCF achieve large performance gains as compared to their counterparts.

关键词： Non-negative matrix factorization concept factorization l(infinity) norm the optimal gradient method sorting-based algorithm

来源：评论

学校读者我要写书评

暂无评论

An Efficient Task Assignment Framework to Accelerate DPU-Based Convolutional Neural Network Inference on FPGAs

引用

IEEE ACCESS 2020年 8卷 83224-83237页

作者： Zhu, Jiang Wang, Lizan Liu, Haolin Tian, Shujuan Deng, Qingyong Li, Jianqi Xiangtan Univ Sch Automat & Elect Informat Xiangtan 411105 Peoples R China Xiangtan Univ Key Lab Hunan Prov Internet Things & Informat Sec Xiangtan 411105 Peoples R China Sci & Technol Parallel & Distributed Proc Lab Xiangtan Peoples R China Hunan Univ Arts & Sci Hunan Prov Cooperat Innovat Ctr Construct & Dev D Changde 415000 Peoples R China

Field Programmable Gate Array (FPGA) has become an efficient accelerator for convolutional neural network (CNN) inference due to its high performance and flexibility. To further improve the performance of CNN inference on FPGAs, an Intellectual Property core (IP core) called Deep Learning processor Unit (DPU) is released by Xilinx. Unlike previous FPGA-based hardware designs focusing on specific functions or CNNs, the DPU IP supports ample basic functions of deep learning, and the developers can take advantage of DPUs to accelerate CNN inference conveniently. In DPU-based CNN acceleration platform, an encapsulated scheduler plays a crucial role in task scheduling between heterogeneous ARM and multiple DPUs. However, the current scheduler is unsatisfactory because its low schedule efficiency. This paper thus presents a high performance task assignment framework built upon Xilinx hybrid CPU-FPGA MPSoC devices. We first evaluate the main causes of low schedule efficiency problem. Then, we explore the scheduler rules and improve shedule efficiency through purposeful observations and analysis. Finally, we integrate our optimizations, and propose an efficient task assignment framework to maximize performance on DPU-based CNN acceleration platform. Experimental results on Xilinx Zynq UltraScale & x002B;MPSoC zcu104 show that our efficient task assignment framework significantly boosts schedule efficiency for small-scale CNNs (from 36 & x0025;to 70 & x0025;), medium-scale CNNs (from 65 & x0025;to 95 & x0025;), and large-scale CNNs (from 77 & x0025;to 99 & x0025;) compared with original schedule strategy.

关键词： Task analysis Acceleration Schedules Field programmable gate arrays Convolutional neural networks Machine learning Hardware Field programmable gate array (FPGA) deep learning processor unit (DPU) convolutional neural network~(CNN) accelerator schedule efficiency

来源：评论

学校读者我要写书评

暂无评论

Non-locally Enhanced Feature Fusion Network for Aircraft Recognition in Remote Sensing Images

引用

REMOTE SENSING 2020年第4期12卷 681-681页

作者： Xiong, Yunsheng Niu, Xin Dou, Yong Qie, Hang Wang, Kang Key Lab Parallel & Distributed Proc Changsha 410005 Peoples R China Natl Univ Def Technol Coll Comp Changsha 410005 Peoples R China

Aircraft recognition has great application value, but aircraft in remote sensing images have some problems such as low resolution, poor contrasts, poor sharpness, and lack of details caused by the vertical view, which make the aircraft recognition very difficult. Especially when there are many kinds of aircraft and the differences between aircraft are subtle, the fine-grained recognition of aircraft is more challenging. In this paper, we propose a non-locally enhanced feature fusion network(NLFFNet) and attempt to make full use of the features from discriminative parts of aircraft. First, according to the long-distance self-correlation in aircraft images, we adopt non-locally enhanced operation and guide the network to pay more attention to the discriminating areas and enhance the features beneficial to classification. Second, we propose a part-level feature fusion mechanism(PFF), which crops 5 parts of the aircraft on the shared feature maps, then extracts the subtle features inside the parts through the part full connection layer(PFC) and fuses the features of these parts together through the combined full connection layer(CFC). In addition, by adopting the improved loss function, we can enhance the weight of hard examples in the loss function meanwhile reducing the weight of excessively hard examples, which improves the overall recognition ability of the network. The dataset includes 47 categories of aircraft, including many aircraft of the same family with slight differences in appearance, and our method can achieve 89.12% accuracy on the test dataset, which proves the effectiveness of our method.

关键词： aircraft recognition remote sensing images non-locally enhanced part-level feature fusion

来源：评论

学校读者我要写书评

暂无评论

Mixup Based Privacy Preserving Mixed Collaboration Learning 13

Mixup Based Privacy Preserving Mixed Collaboration Learning

引用

13th IEEE International Conference on Service-Oriented System Engineering (SOSE) / 10th International Workshop on Joint Cloud Computing (JCC) / IEEE International Workshop on Cloud Computing in Robotic Systems (CCRS)

作者： Fu, Yingwei Wang, Huaimin Xu, Kele Mi, Haibo Wang, Yijie Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Coll Comp Changsha Hunan Peoples R China

ISBN: (数字)9781728114422

ISBN: (纸本)9781728114422

The amount of high-quality data determines the performance of the deep learning model. In reality, the data is often physically distributed in different organizations, and model averaging can train a deep model on the distributed data, while providing competitive performance compared with training a model on the centralized data. However, it cannot prevent inversion attack, as the intermediate parameters are transmitted during training. Some data enhancement methods, such as mixup, can effectively enhance the data privacy. In this paper, we propose a novel model averaging method combined with mixup, which provides protection against inversion attack. Besides we conduct experiments using state-of-the-art deep network architectures on multiple types of dataset to show that our method improves the classification accuracy of models.

关键词： distributed machine learning data privacy protection model aggregation

来源：评论

学校读者我要写书评

暂无评论

Scale-out Acceleration for 3D CNN-based Lung Nodule Segmentation on a Multi-FPGA System 19

Scale-out Acceleration for 3D CNN-based Lung Nodule Segmenta...

引用

56th ACM/EDAC/IEEE Design Automation Conference (DAC)

作者： Shen, Junzhong Wang, Deguang Huang, You Wen, Mei Zhang, Chunyuan Natl Univ Def Technol Coll Comp Natl Key Lab Parallel & Distributed Proc Changsha Hunan Peoples R China

ISBN: (纸本)9781450367257

Three-dimensional convolutional neural networks (3D CNNs) have become a promising method in lung nodule segmentation. The high computational complexity and memory requirements of 3D CNNs make it challenging to accelerate 3D CNNs on a single FPGA. In this work, we focus on accelerating the 3D CNN-based lung nodule segmentation on a multi-FPGA platform by proposing an efficient mapping scheme that takes advantage of the massive parallelism provided by the platform, as well as maximizing the computational efficiency of the accelerators. Experimental results show that our system integrating with four Xilinx VCU118 can achieve state-of-the-art performance of 14.5 TOPS, in addition with a 29.4x performance gain over CPU and 10.5x more energy efficiency over GPU.

关键词： Lung nodule segmentation 3D CNNs multi-FPGA

来源：评论

学校读者我要写书评

暂无评论

Magnetotelluric responses of three-dimensional conductive and magnetic anisotropic anomalies

引用

GEOPHYSICAL PROSPECTING 2020年第3期68卷 1016-1040页

作者： Xiao, Tiaojie Wang, Yun Huang, Xiangyu He, Guoli Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Chinese Acad Sci Inst Geochem State Key Lab Ore Deposit Geochem Guiyang 550002 Guizhou Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Cent S Univ Sch Geosci & Infophys Changsha 410083 Hunan Peoples R China Chinese Acad Sci Inst Geol & Geophys Key Lab Shale Gas & Geoengn Beijing 10029 Peoples R China

A magnetotelluric finite-element modelling algorithm is developed, which is capable of handling three-dimensional conductive and magnetic anisotropic anomalies. Different from earlier three-dimensional magnetotelluric anisotropic modelling methods, the algorithm we presented has taken the magnetic anisotropy into consideration. The variational equations are produced by the Galerkin method and the governing equations are solved using a hexahedral vector edge finite-element method. The accuracy of this algorithm is firstly validated by comparing its solutions with the results of finite-difference method for a three-dimensional conductive arbitrary anisotropic model, and then validated by comparing with analytical solutions for a one-dimensional magnetic model. The responses of four kinds of models under different conditions are studied, and some conclusions are obtained. It shows that for materials with a high magnetic permeability, its influence on magnetotelluric responses cannot be ignored in some circumstances. Especially, if the magnetic susceptibility is exceptionally high, it may really distort the apparent resistivities of lower resistive anomalies. These conclusions are also beneficial for magnetotelluric survey.

关键词： 3D modelling Conductivity anisotropy Finite-element method Magnetotelluric Magnetic anisotropy

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：