检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,958 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

3,004 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,759 篇 工学
- 1,406 篇 计算机科学与技术...
- 685 篇 软件工程
- 489 篇 电气工程
- 396 篇 信息与通信工程
- 202 篇 控制科学与工程
- 130 篇 生物工程
- 78 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 58 篇 机械工程
- 54 篇 仪器科学与技术
- 49 篇 光学工程
- 33 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 24 篇 安全科学与工程
- 23 篇 材料科学与工程（可...
- 22 篇 化学工程与技术
- 20 篇 测绘科学与技术
- 19 篇 石油与天然气工程
516 篇 理学
- 225 篇 物理学
- 189 篇 数学
- 143 篇 生物学
- 58 篇 统计学（可授理学、...
- 40 篇 系统科学
- 27 篇 化学
203 篇 管理学
- 135 篇 管理科学与工程(可...
- 81 篇 图书情报与档案管...
- 31 篇 工商管理
135 篇 医学
- 112 篇 临床医学
- 38 篇 基础医学(可授医学...
37 篇 法学
- 20 篇 社会学
18 篇 文学
14 篇 农学
10 篇 教育学
9 篇 经济学
2 篇 军事学

主题

590 篇 neural networks
173 篇 training
167 篇 artificial neura...
164 篇 deep learning
135 篇 computational mo...
124 篇 feature extracti...
115 篇 neural network
114 篇 convolutional ne...
88 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
74 篇 computer archite...
73 篇 distributed comp...
65 篇 signal processin...
62 篇 distributed proc...
62 篇 accuracy
60 篇 recurrent neural...
55 篇 data models
49 篇 convolutional ne...

机构

11 篇 institute of inf...
9 篇 school of cyber ...
8 篇 univ chinese aca...
8 篇 natl univ def te...
7 篇 college of compu...
7 篇 carnegie mellon ...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
6 篇 department of co...
5 篇 science and tech...
5 篇 ibm tj watson re...
5 篇 school of inform...
5 篇 king saud univer...
5 篇 shandong normal ...
5 篇 kaust thuwal
5 篇 university of ch...
5 篇 natl univ def te...

作者

8 篇 li dongsheng
8 篇 dou yong
8 篇 jie liu
6 篇 richtarik peter
6 篇 ribeiro alejandr...
6 篇 liu jie
6 篇 niu xin
6 篇 yong dou
6 篇 shulian yang
6 篇 zhang wei
5 篇 ryabinin max
5 篇 segarra santiago
5 篇 lai zhiquan
5 篇 ding bo
5 篇 qiao peng
5 篇 xu jiren
5 篇 kokkinos yiannis
5 篇 peng yuxing
5 篇 wang huaimin
5 篇 li aiping

语言

2,925 篇 英文
71 篇 其他
8 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Neural Network and Distributed Processing"

共 3004 条记录，以下是1331-1340 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

CE-Dedup: Cost-Effective Convolutional neural Nets Training based on Image Deduplication

CE-Dedup: Cost-Effective Convolutional Neural Nets Training ...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Xuan Li Liqiong Chang Xue Liu School of Computer Science McGill University Montreal Quebec Canada

Attributed to the ever-increasing large image datasets, Convolutional neural networks (CNNs) have become popular for vision-based tasks. It is generally admirable to have larger-sized datasets for higher network training accuracies. However, the impact of dataset quality has not to be involved. It is reasonable to assume the near-duplicate images exist in the datasets. For instance, the Street View House Numbers (SVHN) dataset having cropped house plate digits from 0 to 9 are likely to have repetitive digits from the same/similar house plates. Redundant images may take up a certain portion of the dataset without consciousness. While contributing little to no accuracy improvement for the CNNs training, these duplicated images unnecessarily pose extra resource and computation consumption. To this end, this paper proposes a framework to assess the impact of the near-duplicate images on CNN training performance, called CE-Dedup. Specifically, CE-Dedup associates a hashing-based image deduplication approach with downstream CNNs-based image classification tasks. CE-Dedup balances the tradeoff between a large deduplication ratio and a stable accuracy by adjusting the deduplication threshold. The effectiveness of CE-Dedup is validated through extensive experiments on well-known CNN benchmarks. On one hand, while maintaining the same validation accuracy, CE-Dedup can reduce the dataset size by 23%. On the other hand, when allowing a small validation accuracy drop (by 5%), CE-Dedup can trim the dataset size by 75%.

关键词： Training Benchmark testing Convolutional neural networks Task analysis Image classification

来源：评论

学校读者我要写书评

暂无评论

1st International Workshop on Multiple-Aspect Analysis of Semantic Trajectories, MASTER 2019 held in Conjunction with the 19th European conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019

1st International Workshop on Multiple-Aspect Analysis of Se...

引用

1st International Workshop on Multiple-Aspect Analysis of Semantic Trajectories, MASTER 2019 held in Conjunction with the 19th European conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019

ISBN: (纸本)9783030380809

The proceedings contain 9 papers. The special focus in this conference is on Multiple-Aspect Analysis of Semantic Trajectories. The topics include: Uncovering Hidden Concepts from AIS Data: A network Abstraction of Maritime Traffic for Anomaly Detection;learning from Our Movements – The Mobility Data Analytics Era;preface;multi-channel Convolutional neural networks for Handling Multi-dimensional Semantic Trajectories and Predicting Future Semantic Locations;A Neighborhood-Augmented LSTM Model for Taxi-Passenger Demand Prediction;predicting Fishing Effort and Catch Using Semantic Trajectories and Machine Learning;prospective Data Model and distributed Query processing for Mobile Sensing Data Streams.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Computer Modeling, Simulation and Algorithm - Image processing, Pattern Recognition and Artificial Intelligence

2nd International Conference on Computer Modeling, Simulatio...

引用

2020 2nd International conference on Computer Modeling, Simulation and Algorithm, CMSA 2020

The proceedings contain 261 papers. The topics discussed include: MBSE-based modeling technology for aircraft assembly tooling design demand;modeling and implementation of distributed rain water storage and utilization;modeling free surface elevation around tandem piers of the longitudinal bridge by computational fluid dynamics;L1-finite difference method for inverse source problem of fractional diffusion equation;EMD and singular value difference spectrum based bearing fault characteristics extraction;research on a distribution-outlier detection algorithm based on logistics distribution data;activation detection algorithms for pattern division multiple access uplink grant-free transmission;application of enhanced whale adaptive threshold noise reduction method in transformer ultrasonic 3D imaging detection;human body shape reconstruction from binary image using convolutional neural network;a pricing mechanism which implements allocation in Shannon formula of home cellular wireless communication;and research on power consumption information acquisition system based on broadband power line carrier technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Field Independent Target Classification Analysis in distributed Acoustic Sensing Systems 27

Field Independent Target Classification Analysis in Distribu...

引用

27th Signal processing and Communications Applications conference (SIU)

作者： Maral, Hakan Aktas, Metin ASELSAN Ulasim Guvenlik Enerji & Otomasyon Sistemleri UGES Sekt Baskanligi Ankara Turkey

ISBN: (纸本)9781728119045

In this paper, we are able to focus on the fiber-optic distributed acoustic systems required to isolate the oil and gas pipeline, remote areas, facilities and lines in the area. Threatening performances of network structures of different complexity and depth. All measurements, the criteria for working independently from the field, the results obtained and the results obtained and on-site troubleshooting methods in different geographical areas. It analyzes the performance results and shows a high performance network in the field in real time.

关键词： distributed acoustic sensing phase-OTDR deep learning convolutional neural networks CNN threat detection threat classification

来源：评论

学校读者我要写书评

暂无评论

MapReduce-based Capsule networks 6

MapReduce-based Capsule Networks

引用

6th International conference on Social networks Analysis, Management and Security (SNAMS)

作者： Park, Sun Jin Park, Ho-Hyun LG CNS Seoul South Korea Chung Ang Univ Sch Elect & Elect Engn Seoul South Korea

ISBN: (纸本)9781728129464

Currently, artificial intelligence technology is attracting much attention, and image processing field is also making remarkable progress in recognition rate through CNN models. Furthermore, Capsule network which is flexible in changing pose of image is being studied in various fields by improving disadvantage of Pooling Layer of CNN model. We propose a method to accelerate the learning of CapsNet model, which is much slower than the existing neural network model. TensorFlow, Google's deep-running library, and the Apache Foundation's Hadoop framework are run through Python. We can confirm that the learning time is decreased in inverse proportion to the increase of the number of nodes in learning CapsNet according to the proposed method of distributed processing.

关键词： distributed processing Training GPU Acceleration neural network Capsule network

来源：评论

学校读者我要写书评

暂无评论

SPINN: Synergistic progressive inference of neural networks over device and cloud 20

SPINN: Synergistic progressive inference of neural networks ...

引用

26th Annual International conference on Mobile Computing and networking, MobiCom 2020

作者： Laskaridis, Stefanos Venieris, Stylianos I. Almeida, Mario Leontiadis, Ilias Lane, Nicholas D. Samsung AI Center Cambridge United Kingdom University of Cambridge United Kingdom

ISBN: (纸本)9781450370851

Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices. A popular alternative comprises offloading CNN processing to powerful cloud-based servers. Nevertheless, by relying on the cloud to produce outputs, emerging mission-critical and high-mobility applications, such as drone obstacle avoidance or interactive applications, can suffer from the dynamic connectivity conditions and the uncertain availability of the cloud. In this paper, we propose SPINN, a distributed inference system that employs synergistic device-cloud computation together with a progressive inference method to deliver fast and robust CNN inference across diverse settings. The proposed system introduces a novel scheduler that co-optimises the early-exit policy and the CNN splitting at run time, in order to adapt to dynamic conditions and meet user-defined service-level requirements. Quantitative evaluation illustrates that SPINN outperforms its state-of-the-art collaborative inference counterparts by up to 2× in achieved throughput under varying network conditions, reduces the server cost by up to 6.8× and improves accuracy by 20.7% under latency constraints, while providing robust operation under uncertain connectivity conditions and significant energy savings compared to cloud-centric execution. © 2020 ACM.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient distributed Blockwise Momentum SGD with Error-Feedback 33

Communication-Efficient Distributed Blockwise Momentum SGD w...

引用

33rd conference on neural Information processing Systems (NeurIPS)

作者： Zheng, Shuai Huang, Ziyue Kwok, James T. Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Amazon Web Serv Seattle WA 98109 USA

Communication overhead is a major bottleneck hampering the scalability of distributed machine learning systems. Recently, there has been a surge of interest in using gradient compression to improve the communication efficiency of distributed neural network training. Using 1-bit quantization, signSGD with majority vote achieves a 32x reduction on communication cost. However, its convergence is based on unrealistic assumptions and can diverge in practice. In this paper, we propose a general distributed compressed SGD with Nesterov's momentum. We consider two-way compression, which compresses the gradients both to and from workers. Convergence analysis on nonconvex problems for general gradient compressors is provided. By partitioning the gradient into blocks, a blockwise compressor is introduced such that each gradient block is compressed and transmitted in 1-bit format with a scaling factor, leading to a nearly 32x reduction on communication. Experimental results show that the proposed method converges as fast as full-precision distributed momentum SGD and achieves the same testing accuracy. In particular, on distributed ResNet training with 7 workers on the ImageNet, the proposed algorithm achieves the same testing accuracy as momentum SGD using full-precision gradients, but with 46% less wall clock time.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Revealing and protecting labels in distributed training 21

Revealing and protecting labels in distributed training

引用

Proceedings of the 35th International conference on neural Information processing Systems

作者： Trung Dang Om Thakkar Swaroop Ramaswamy Rajiv Mathews Peter Chin Françoise Beaufays Boston University Google

ISBN: (纸本)9781713845393

distributed learning paradigms such as federated learning often involve transmission of model updates, or gradients, over a network, thereby avoiding transmission of private data. However, it is possible for sensitive information about the training data to be revealed from such gradients. Prior works have demonstrated that labels can be revealed analytically from the last layer of certain models (e.g., ResNet), or they can be reconstructed jointly with model inputs by using Gradients Matching [1] with additional knowledge about the current state of the model. In this work, we propose a method to discover the set of labels of training samples from only the gradient of the last layer and the id to label mapping. Our method is applicable to a wide variety of model architectures across multiple domains. We demonstrate the effectiveness of our method for model training in two domains - image classification, and automatic speech recognition. Furthermore, we show that existing reconstruction techniques improve their efficacy when used in conjunction with our method. Conversely, we demonstrate that gradient quantization and sparsification can significantly reduce the success of the attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Framework for Deep Q-Learning Based Hybrid DVFS Algorithms for Real-Time Systems

A Framework for Deep Q-Learning Based Hybrid DVFS Algorithms...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Ke Yu Hongwang Xiao Ying Zhao Jiao Tian Jinjun Chen Swinburne University of Technology Hawthorn VIC Australia

In real-time systems, energy consumption is one of the most critical challenges. Dynamic voltage and frequency scaling (DVFS) algorithms have been widely applied to balance the trade-off between performance and power consumption. We first review some classic DVFS methods, e.g., LA-EDF and CCEDF, and then a hybrid DVFS algorithm (Soft-LA2) that we proposed recently. Soft-LA2 needs domain knowledge to set the trade-off parameter manually to achieve energy saving compared with classic methods. Motivated by recent deep learning technologies applied in DVFS, in this paper, we propose a new framework for Soft-LA2. Our method automatically optimizes parameters for Soft-LA2, which leads to more power saving compared with random parameter setting in Soft-LA2. Simulation results show that under certain neural network architecture setting, our method can find the best parameters automatically to achieve power saving performance. Furthermore, with test data, our proposed method saves 4.9% and 9.6% power consumption compared with relevant learning method DQL-EES and random setting Soft-LA2, respectively.

关键词： Training Q-learning Power demand Heuristic algorithms Simulation neural networks Voltage

来源：评论

学校读者我要写书评

暂无评论

FGPA: Fine-Grained Pipelined Acceleration for Depthwise Separable CNN in Resource Constraint Scenarios

FGPA: Fine-Grained Pipelined Acceleration for Depthwise Sepa...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Chunhua Xiao Dandan Xu Shi Qiu Chen Shi Kun Ning College of Computer Science Chongqing University Chongqing China

Depthwise Separable Convolution can effectively reduce parameters and operations with little loss in precision, which becomes more and more popular in many innovative neural networks such as MobileNet and Xception. Due to limited computing resources and storage space, how to deploy Depthwise Separable CNN(DSCNN) in a more efficient manner for resource constraint scenarios is still an open and important problem to be explored. In this paper, a Fine-Grained Pipelined Acceleration scheme (FGPA) is proposed. Different from existing works, we partition the DSCNN accelerator into multiple computational modules that support fine-grained operations according to resource constraint and data dependency analysis, which is able to support starting next layer computation before previous layer completion. Along with the proposed scheduling strategy Start as Soon as Possible (SSP), we can accelerate DSCNN in a pipelined parallel manner, and all the intermediate data between layers can be kept on-chip memory to avoid the stream-out cost. In this way, we can not only improve the utilization of on-chip memory and computing resources but also reduce the network computational delay. As a case study, MobileNetV1 is implemented on Zynq XC7Z045. Experimental results indicate that the proposed DSCNN accelerator can achieve 99.68 GOPS and 0.17 GOPS/DSP under 250MHz clock frequency.

关键词： Costs Processor scheduling Convolution neural networks Hardware System-on-chip Delays

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共301页 << < 130 131 132 133 134 135 136 137 138 139 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：