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

2,976 篇 会议
38 篇 期刊文献
7 册 图书

馆藏范围

3,021 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,758 篇 工学
- 1,406 篇 计算机科学与技术...
- 684 篇 软件工程
- 490 篇 电气工程
- 397 篇 信息与通信工程
- 203 篇 控制科学与工程
- 130 篇 生物工程
- 77 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
- 48 篇 光学工程
- 33 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 23 篇 安全科学与工程
- 22 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
515 篇 理学
- 224 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
202 篇 管理学
- 134 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

591 篇 neural networks
179 篇 training
169 篇 artificial neura...
168 篇 deep learning
142 篇 computational mo...
129 篇 feature extracti...
123 篇 convolutional ne...
115 篇 neural network
88 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
75 篇 computer archite...
74 篇 distributed comp...
73 篇 accuracy
65 篇 signal processin...
62 篇 distributed proc...
61 篇 data models
61 篇 recurrent neural...
49 篇 biological neura...

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 department of co...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
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

2,814 篇 英文
199 篇 其他
11 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 3021 条记录，以下是1241-1250 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：

PANDA: Population Automatic neural distributed Algorithm for Deep Leaning

PANDA: Population Automatic Neural Distributed Algorithm for...

引用

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

作者： Jia Wei Xingjun Zhang Zeyu Ji Jingbo Li Zheng Wei High Performance Computing Lab Xi’an Jiaotong University Xi’an China

Deep neural network models perform very brightly in the field of artificial intelligence, but their success is affected by hyperparameters, and the learning rate schedule is one of the most important hyperparameters, and the search for the learning rate schedule is often time-consuming and computationally resource-intensive. In this paper, we propose a Population Automatic neural distributed Algorithm (PANDA) based on population joint optimization, which uses distributed data parallel deep neural network training to implement a dynamic learning rate schedule optimization strategy based on the population idea, with almost no loss of test accuracy, PANDA is able to dynamically refine the learning rate schedule during model training instead of following the usual suboptimal strategy. We conducted experiments on typical AlexNet, VGG16, and ResNet18 using the Tianhe-3 supercomputing prototype, and the results show that using PANDA to dynamically update the learning rate greatly reduces the learning rate schedule search time while ensuring close performance with the latest population hyperparameter algorithm, and in our experiments, PANDA lead to at max 123.85x speedup, and the experimental results prove the effectiveness and robustness of PANDA.

关键词： Training Deep learning Schedules Heuristic algorithms Sociology Learning (artificial intelligence) Statistics

来源：评论

学校读者我要写书评

暂无评论

ACM International conference Proceeding Series

ACM International Conference Proceeding Series

引用

49th International conference on Parallel processing, ICPP 2020

ISBN: (纸本)9781450388160

The proceedings contain 78 papers. The topics discussed include: Huffman coding with gap arrays for GPU acceleration;SkyChain: a deep reinforcement learning-empowered dynamic blockchain sharding system;GOSH: embedding big graphs on small hardware;CARD: a congestion-aware request dispatching scheme for replicated metadata server cluster;safe, fast sharing of memcached as a protected library;DQEMU: a scalable emulator with retargetable DBT on distributed platforms;Shadowtutor: distributed partial distillation for mobile video DNN inference;FEEL: a federated edge learning system for efficient and privacy-preserving mobile healthcare;adaptive distributed convolutional neural network inference at the network edge with ADCNN;an efficient wear-level architecture using self-adaptive wear leveling;and CCHL: compression-consolidation hardware logging for efficient failure-atomic persistent memory updates.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STARGAZER: A Deep Learning Approach for Estimating the Performance of Edge-Based Clustering Applications

STARGAZER: A Deep Learning Approach for Estimating the Perfo...

引用

IEEE International conference on Smart Data Services (SMDS)

作者： Cruz, Breno Dantas Paul, Arnab K. Song, Zheng Tilevich, Eli Virginia Tech Software Innovat Lab Blacksburg VA 24061 USA Virginia Tech Distributed Syst & Storage Lab Blacksburg VA 24061 USA

ISBN: (纸本)9781728187778

As a solution to the sensor data deluge, edge computing processes sensor data by means of local devices. Many of these devices are resource-scarce in terms of the available processing capabilities and battery power. To achieve the required design trade-offs of edge applications, developers must be able to understand the performance and resource utilization of data processing algorithms. An increasing number of edge-based applications use machine learning (ML) as their key functionality. However, the performance and resource utilization of ML algorithms remain poorly understood, thus hindering the system design of edge-based ML applications. In addition, developers often cannot access real-world edge-based test beds during the design phase. To address this problem, we present an approach for estimating the performance of edge-based ML applications, with a particular application to clustering. To that end, we first comprehensively evaluate the performance and resource utilization of widely used clustering algorithms deployed in a representative edge environment. Second, we identify which properties of these algorithms are correlated with their performance and resource utilization. Finally, we apply our findings to create STARGAZER, a Deep neural network that given a clustering algorithm's computational load and input data size, estimates how this algorithm would perform and utilize resources in an edge-based application. Our tool provides viable decision-making support for addressing the multifaceted design challenges of edge-based ML applications.

关键词： Edge Applications Machine Learning Clustering Algorithms Performance Estimation Deep neural network

来源：评论

学校读者我要写书评

暂无评论

Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent neural Tangent Kernels

Wearing A Mask: Compressed Representations of Variable-Lengt...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Sina Alemohammad Hossein Babaei Randall Balestriero Matt Y. Cheung Ahmed Imtiaz Humayun Daniel LeJeune Naiming Liu Lorenzo Luzi Jasper Tan Zichao Wang Richard G. Baraniuk Rice University

High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation. Techniques abound to reduce the dimensionality of fixed-length sequences, yet these methods rarely generalize to variable-length sequences. To address this gap, we extend existing methods that rely on the use of kernels to variable-length sequences via use of the Recurrent neural Tangent Kernel (RNTK). Since a deep neural network with ReLu activation is a Max-Affine Spline Operator (MASO), we dub our approach Max-Affine Spline Kernel (MASK). We demonstrate how MASK can be used to extend principal components analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) and apply these new algorithms to separate synthetic time series data sampled from second-order differential equations.

关键词： Dimensionality reduction Time series analysis neural networks Natural languages Signal processing algorithms Signal processing Kernel

来源：评论

学校读者我要写书评

暂无评论

Understanding the Runtime Overheads of Deep Learning Inference on Edge Devices

Understanding the Runtime Overheads of Deep Learning Inferen...

引用

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

作者： Xiu Ma Guangli Li Lei Liu Huaxiao Liu Xiaobing Feng College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

With the growing ubiquity of the Internet of Things, in-the-edge inference of deep neural network models has been a major driver for promoting the widespread use of intelligent applications. As model inference characteristics are crucial for optimizing and deploying deep neural networks on hardware platforms, many studies focus on analyzing the performance of neural networks such as latency, accuracy, throughput, and energy consumption. However, few existing works have ever discussed the runtime overheads hidden in neural network inference, despite the overheads are non-negligible for edge applications. The lack of in-depth analysis of the overheads hinders the understanding of how hardware designs and model structures impact on-device inference performance. In this paper, we characterize the runtime overheads of deep learning inference on representative edge devices by leveraging state-of-the-art neural network models, performing a systematical analysis from the perspective of end-to-end performance, hardware platforms, memory bandwidth, and neural network model structures. Based on experimental results, the crucial insights are offered to facilitate the design and configure of resource-efficient networks and pick appropriate models on the specific platform, which provides a comprehensive view of runtime overheads of in-the- edge neural network inference for architects and developers.

关键词： Deep learning Performance evaluation Analytical models Runtime Roads neural networks Throughput

来源：评论

学校读者我要写书评

暂无评论

2020 International conference on High Performance Big Data and Intelligent Systems, HPBD and IS 2020

2020 International Conference on High Performance Big Data a...

引用

2020 International conference on High Performance Big Data and Intelligent Systems, HPBD and IS 2020

ISBN: (纸本)9781728165110

The proceedings contain 32 papers. The topics discussed include: M-IDAs: a scalable and droppable big data intelligent platform based on modular design;a method of automatically recognizing CTF image and calculating value;parameter identification of collaborative robot based on improved artificial fish swarm algorithm;a novel bearing fault diagnosis of raw signals based on 1D residual convolution neural network;face liveness detection algorithm based on livenesslight network;erasure-code algorithm for distributed stream processing;an intelligent ordering control system based on hand gesture recognition;PLS-VIO: stereo vision-inertial odometry based on point and line features;and SSD assisted caching for restore optimization in distributed deduplication environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of distributed Deep Learning Frameworks in a Multi-GPU Environment

Performance Analysis of Distributed Deep Learning Frameworks...

引用

International conference on Ubiquitous Computing and Communications and International Symposium on Cyberspace and Security (IUCC-CSS)

作者： Tulasi Kavarakuntla Liangxiu Han Huw Lloyd Annabel Latham Samson B. Akintoye Manchester Metropolitan University Manchester UK

ISBN: (纸本)9781665466684

Deep Learning frameworks, such as TensorFlow, MXNet, Chainer, provide many basic building blocks for designing effective neural network models for various applications (e.g. computer vision, speech recognition, natural language processing). However, run-time performance of these deep learning frameworks varies significantly even when training identical deep network models on the same GPUs. This study presents an experimental analysis and performance model for assessing deep learning models (Convolutional neural networks (CNNs), Multilayer Perceptrons (MLP), Autoencoder) on three frameworks: TensorFlow, MXNet, and Chainer, in a multi-GPU environment. We analyse factors that influence these frameworks' performance by computing the running time of each framework in our proposed model, taking load imbalance factor into account. The evaluation results highlight significiant differences in the scalability of the frameworks, and the importance of load balance in parallel distributed deep learning.

关键词： Deep learning Training Analytical models Computational modeling Scalability neural networks Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A Predictive Real-Time Short-Term Battery Scheduling Method for Peak Load Shaving in Residential distributed Energy Storage Systems

A Predictive Real-Time Short-Term Battery Scheduling Method ...

引用

Smart Grid conference (SGC)

作者： Arash Barzkar Ashkan Barzkar Seyed Mohammad Hassan Hosseini South Tehran Branch Islamic Azad University Tehran Iran Virginia Tech Blacksburg USA

ISBN: (纸本)9781665401661

Providing a smooth power demand in many applications is necessary so as to maintain the Grid stability. Peak load shaving is a method in demand side management (DSM) requiring information on the future load profile data and forecasting methods. In this paper, an artificial neural network short-term load forecasting (ANNSTLF) method is adapted in order to apply forecasted load demand data to a previously discussed non-predictive real-time battery scheduling peak load shaving system. The introduced algorithm aims to provide peak load shaving and load smoothing in residential areas and can be considered for small processing systems. The ANNSTLF is implemented in a non-predictive peak load shaving algorithm, where uses profile data of a residual for a year to train the artificial neural network (ANN) to forecast the day ahead load demand. In order to assess the performance of the proposed method, simulations in MATLAB are done and predictive and the non-predictive approaches results are compared to each other.

关键词： Smoothing methods Load forecasting distributed databases Artificial neural networks Reservoirs Real-time systems Stability analysis

来源：评论

学校读者我要写书评

暂无评论

The Capability of Wavelet Convolutional neural network for Detecting Cyber Attack of distributed Denial of Service in Smart Grid

The Capability of Wavelet Convolutional Neural Network for D...

引用

International conference on Wavelet Active Media Technology and Information processing (ICWAMTIP)

作者： Happy Nkanta Monday Jian Ping Li Grace Ugochi Nneji Abel Zenebe Yutra Bona Debela Lemessa Saifun Nahar Edidiong Christopher James Amin Ul Haq School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu Sichuan China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu Sichuan China School of Computer and Information Systems University of Missouri St Louis MO USA

ISBN: (纸本)9781665413657

The electrical system's dependability, security, and efficiency are all improved through smart grid technologies. Its dependence on digital communication technology, on the other hand, introduces new risks and vulnerabilities that should be examined for the purpose to providing effective and trustworthy service delivery. This study presents a method for the detection of distributed denial of service (DDoS) attacks on smart grid infrastructure. Continuous wavelet transform (CWT) is used in the suggested approach to convert one-dimensional traffic data to two-dimensional time-frequency domain scalogram as the input to the wavelet convolutional neural network (WavCovNet) to detect anomalous behavior in the data by distinguishing attack features from normal patterns. Our results demonstrate that the proposed approach detects DDoS attacks with a high rate of detection and with a very low rate of false alarm.

关键词： Time-frequency analysis Continuous wavelet transforms Wavelet domain Information processing Media Denial-of-service attack Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Load Balancing Applying BPN in a Dual-Core Processor in IP Router Running with QUEST Scheduler 2nd

Load Balancing Applying BPN in a Dual-Core Processor in IP R...

引用

2nd International conference on Communication, Devices and Computing (ICCDC)

作者： Paul, Suman Pandit, Malay Kumar Haldia Inst Technol Dept ECE Haldia W Bengal India West Bengal Univ Technol Sch Engn & Technol Maulana Abul Kalam Azad Univ Technol West Bengal Kolkata India

ISBN: (纸本)9789811508295;9789811508288

In this paper, we investigate on a load balancing scheme applying neural network-backpropagation network (BPN) algorithm in a dual-core processor in IP router for processing of multimedia IP traffic. Load balancing is an important challenging issue among the cores of a processor in network routers. A balanced equally distributed and a steady-state load of the cores enhances the system quality of service (QoS) and performance. In this system, each core runs with a QoS-enhanced stochastic smart packet scheduler-QUEST. For analysis, we take both the cases of moderately and heavily unbalanced initial load of the cores of a dual-core processor in router. Each core is provisioned with the QUEST scheduler and runs to attain a ratio of process utilization which is of steady-state featured for scheduling and processing of multimedia IP traffic, namely, deadline-sensitive Voice over Internet Protocol, Internet Protocol Television, and best-effort Hypertext Transfer Protocol. We observe the computed balanced load applying the BPN for different conditions. Applying BPN, the load imbalance among the cores is minimized and the results show that load of each core has attained a target steady-state balanced load.

关键词： Backpropagation network (BPN) Dual-core processor in IP router Load balancing network QoS Scheduler

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303页 << < 121 122 123 124 125 126 127 128 129 130 > >>

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：