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

2,236 篇 会议
13 册 图书
5 篇 期刊文献

馆藏范围

2,254 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,606 篇 工学
- 1,382 篇 计算机科学与技术...
- 966 篇 软件工程
- 321 篇 控制科学与工程
- 241 篇 信息与通信工程
- 218 篇 电气工程
- 177 篇 生物工程
- 129 篇 生物医学工程（可授...
- 91 篇 机械工程
- 76 篇 交通运输工程
- 57 篇 光学工程
- 50 篇 电子科学与技术（可...
- 43 篇 化学工程与技术
- 42 篇 安全科学与工程
- 35 篇 仪器科学与技术
- 32 篇 土木工程
466 篇 理学
- 237 篇 数学
- 182 篇 生物学
- 101 篇 统计学（可授理学、...
- 81 篇 物理学
- 47 篇 系统科学
- 41 篇 化学
434 篇 管理学
- 287 篇 管理科学与工程(可...
- 162 篇 图书情报与档案管...
- 79 篇 工商管理
170 篇 医学
- 163 篇 临床医学
- 81 篇 基础医学(可授医学...
- 54 篇 药学(可授医学、理...
- 34 篇 公共卫生与预防医...
76 篇 教育学
- 74 篇 教育学
49 篇 法学
- 44 篇 社会学
30 篇 经济学
18 篇 农学
2 篇 军事学

主题

173 篇 machine learning
160 篇 deep learning
135 篇 training
100 篇 data models
78 篇 feature extracti...
76 篇 accuracy
70 篇 data mining
67 篇 neural networks
66 篇 predictive model...
61 篇 reinforcement le...
57 篇 computational mo...
52 篇 support vector m...
46 篇 real-time system...
42 篇 machine learning...
39 篇 training data
39 篇 artificial intel...
36 篇 visualization
35 篇 learning systems
35 篇 adaptation model...
31 篇 big data

机构

18 篇 kazan natl res t...
12 篇 king mongkuts un...
10 篇 institute of inf...
9 篇 school of cyber ...
7 篇 chitkara univers...
7 篇 college of compu...
6 篇 king mongkuts un...
6 篇 department of co...
6 篇 the key laborato...
5 篇 chinese acad sci...
5 篇 department of co...
5 篇 department of co...
4 篇 peng cheng lab
4 篇 univ chinese aca...
4 篇 department of ci...
4 篇 school of electr...
4 篇 department of el...
4 篇 school of inform...
4 篇 univ chinese aca...
4 篇 school of comput...

作者

7 篇 yang qiang
7 篇 piriyasurawong p...
6 篇 ouya samuel
6 篇 akatimagool soms...
5 篇 mendy gervais
5 篇 cortez paulo
5 篇 kraysman natalia...
4 篇 peng shaoliang
4 篇 liu sheng
4 篇 you linlin
4 篇 li han
4 篇 barabanova svetl...
4 篇 wang wei
4 篇 huang kaiqi
4 篇 lei baiying
4 篇 wang jinyan
4 篇 khatsrinova olga...
4 篇 shen dinggang
4 篇 li wei
4 篇 li qianmu

语言

2,155 篇 英文
93 篇 其他
27 篇 中文
1 篇 葡萄牙文

检索条件"任意字段=22nd International Conference on Intelligent Data Engineering and Automated Learning"

共 2254 条记录，以下是1841-1850 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：

Timed dataflow: Reducing communication overhead for distributed machine learning systems 22

Timed dataflow: Reducing communication overhead for distribu...

引用

22nd IEEE international conference on Parallel and Distributed Systems, ICPADS 2016

作者： Sun, Peng Wen, Yonggang Duong, Ta Nguyen Binh Yan, Shengen Energy Research Institute Interdisciplinary Graduate School Nanyang Technological University Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Sensetime Group Limited Shatin N.T. Hong Kong

ISBN: (纸本)9781509044573

Many distributed machine learning (ML) systems exhibit high communication overhead when dealing with big data sets. Our investigations showed that popular distributed ML systems could spend about an order of magnitude more time on network communication than computation to train ML models containing millions of parameters. Such high communication overhead is mainly caused by two operations: pulling parameters and pushing gradients. In this paper, we propose an approach called Timed dataflow (TDF) to deal with this problem via reducing network traffic using three techniques: a timed parameter storage system, a hybrid parameter filter and a hybrid gradient filter. In particular, the timed parameter storage technique and the hybrid parameter filter enable servers to discard unchanged parameters during the pull operation, and the hybrid gradient filter allows servers to drop gradients selectively during the push operation. Therefore, TDF could reduce the network traffic and communication time significantly. Extensive performance evaluations in a real testbed showed that TDF could reduce up to 77% and 79% of network traffic for the pull and push operations, respectively. As a result, TDF could speed up model training by a factor of up to 4 without sacrificing much accuracy for some popular ML models, compared to systems not using TDF. © 2016 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Collaborative Q-learning based routing control in unstructured P2P networks 22nd

Collaborative Q-learning based routing control in unstructur...

引用

22nd international conference on MultiMedia Modeling, MMM 2016

作者： Shen, Xiang-Jun Chang, Qing Gou, Jian-Ping Mao, Qi-Rong Zha, Zheng-Jun Lu, Ke School of Computer Science and Telecommunication Engineering Jiangsu University Zhenjiang212013 China Institute of Intelligent Machines Chinese Academy of Sciences Hefei Anhui China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783319276700

Query routing among peers whilst locating required resources is still an acute issue discussed P2P networking, especially in unstructured P2P networks. Such an issue becomes worse when there is frequent in and out movement of the peers in the network and also with node failures. We propose a new method to assure alternative routing path to balance the query loads among the peers under higher network churns. The proposed collaborative Q-learning method learns the networks parameters such as processing capacity, number of connections, and number of resources in the peers, along with their state of congestion. By this technique, peers are avoided to forward queries to the congested peers. Our simulation results show that the required resources are located more quickly and queries in the whole network are also balanced. Also our proposed protocol exhibits more robustness and adaptability under high network churns and heavy workloads than that of the random walk method. © Springer international Publishing Switzerland 2016.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Accelerating Deep learning with Shrinkage and Recall

Accelerating Deep Learning with Shrinkage and Recall

引用

international conference on Parallel and Distributed Systems (ICPADS)

作者： Shuai Zheng Abhinav Vishnu Chris Ding Department of Computer Science and Engineering University of Texas at Arlington TX USA Pacific Northwest National Laboratory Richland WA USA

ISBN: (纸本)9781509053827

Deep learning is a very powerful machine learning model. Deep learning trains a large number of parameters for multiple layers and is very slow when data is in large scale and the architecture size is large. Inspired from the shrinking technique used in accelerating computation of Support Vector Machines (SVM) algorithm and screening technique used in LASSO, we propose a shrinking Deep learning with recall (sDLr) approach to speed up deep learning computation. We experiment shrinking Deep learning with recall (sDLr) using Deep Neural Network (DNN), Deep Belief Network (DBN) and Convolution Neural Network (CNN) on 4 data sets. Results show that the speedup using shrinking Deep learning with recall (sDLr) can reach more than 2.0 while still giving competitive classification performance.

关键词： Machine learning Training data Training Biological neural networks Support vector machines Acceleration Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Research on MAC layer communication performance model of wireless sensor networks for intelligent transportation

Research on MAC layer communication performance model of wir...

引用

international conference on Automation and Computing (ICAC)

作者： Zhong Chu Wei Sun Jianping Wang Department of Electronic Information & Electric Engineering Hefei University Hefei China School of Electrical Engineering and Automation Hefei University of Technology Hefei China Hefei China

With the development of MEMS (Micro-electromechanical Systems), the wireless sensor networks (WSNs) have become an important communicating method for intelligent transportation application. Mathematics modeling, as an effective quantitative analysis method, is very important for conducting intelligent transportation performance research when WSNs are applied. Based on the channel contention mechanism of IEEE802.15.4 standard Media Access Control (MAC) layer unslotted mode, MAC layer mathematics performance model of throughput, goodput, average delay and collision rate is built by analyzing the state of node buffer, state of nodes, and the state of channel. In addtion, the MAC layer mathematics models and corresponding performance are simulated in MATLAB and QualNet respectively. The simulation results indicate that the mathematics models can be used for the real communication quantitative analysis of WSNs MAC layer communication.

关键词： Mathematical model Wireless sensor networks Analytical models Throughput data models Delays

来源：评论

学校读者我要写书评

暂无评论

Research on Semi-Supervised learning for Hyperspectral Remote Sensing Imaging Classification Base on Confidence Entropy

Research on Semi-Supervised Learning for Hyperspectral Remot...

引用

international conference on Parallel and Distributed Systems (ICPADS)

作者： Chunyang Wang Zhifang Xu Shuangting Wang Hebing Zhang Zhichao Chen National Administration of Surveying Henan Polytechnic University Jiaozuo China School of Surveying and Land Information Engineering Henan Polytechnic University Jiaozuo China

ISBN: (纸本)9781509053827

The research of Hyperspectral classification is the hotpots at present. In this article, an effective semi-supervised classification method was proposed for hyperspectral image based on confidence entropy. The experimental results show that the proposed method can effectively improve the accuracy of classification and obtain better classification results for hyperspectral image data using few labeled samples.

关键词： Hyperspectral imaging Entropy Mathematical model Support vector machines Training

来源：评论

学校读者我要写书评

暂无评论

Least-squares learning control with guaranteed parameter convergence

Least-squares learning control with guaranteed parameter con...

引用

international conference on Automation and Computing (ICAC)

作者： Yongping Pan Xiang Li Haoyong Yu Department of Biomedical Engineering National University of Singapore Singapore Singapore

Parameter convergence is of great importance as it enhances the overall stability and robustness properties of adaptive control systems. However, a stringent persistent-excitation (PE) condition usually has to be satisfied to achieve parameter convergence in adaptive control. In this paper, a least-squares learning control strategy without regressor filtering is presented to achieve parameter convergence at the absence of the PE condition. An additional modified modeling error that utilizes online recorded data is constructed to update parametric estimates, and an integral transformation is derived to avoid the time differentiation of plant states in the computation of the modified modeling error. An indirect adaptive control law equipped with a novel filtering-free least-squares estimation is proposed to guarantee exponential convergence of both tracking errors and parameter estimation errors by an interval-excitation (IE) condition which is much weaker than the PE condition. An illustrative example has verified effectiveness of the proposed approach.

关键词： Adaptive control Convergence Estimation Parameter estimation Adaptation models Computational modeling data models

来源：评论

学校读者我要写书评

暂无评论

Machine learning-Based Image Classification for Wireless Camera Sensor Networks

Machine Learning-Based Image Classification for Wireless Cam...

引用

IEEE international conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)

作者： Jungmo Ahn Jeongyeup Paek JeongGil Ko Department of Software and Computer Engineering Ajou University School of Computer Engineering Chung-Ang University

ISBN: (纸本)9781509024803

Wireless sensor networks, with their capability to capture physical phenomena at micro-scale, have changed how we collect and analyze data from the real world. Especially, using low-power cameras we can design interesting applications that provide us with previously difficult-to-capture information from the real-world. While cameras hold privacy threats in human-residing environments, they can be actively used in natural world analyzing applications. However, the disadvantage of using cameras is that the samples themselves (e.g., images) have large sizes, forcing the system to exchange more data, and in turn, decreasing energy efficiency. Given that camera-based sensor networks are usually deployed in remote locations, the lifetime of individual devices become a major concern. In this work, we target to utilize machine-learning algorithms to characterize the context of images captured from a real-world deployments. Specifically, using images from the James Reserve bird nest deployment [1], we utilize and optimize machine learning algorithms to operate on embedded low-power, resource-limited platforms. Using both a systematic and algorithmic approach, our proposed systems architecture and algorithms hold the potential to reduce the amount of data to be transmitted by as much a eight-fold.

关键词： Cameras Birds Machine learning algorithms Systems architecture Servers Histograms Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Very Low-Resolution Face Recognition via Semi-Coupled Locality-Constrained Representation

Very Low-Resolution Face Recognition via Semi-Coupled Locali...

引用

international conference on Parallel and Distributed Systems (ICPADS)

作者： Tao Lu Wei Yang Yanduo Zhang Xiaolin Li Zixiang Xiong Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Department of Electrical and Computer Engineering Texas A&M University College Station TX

ISBN: (纸本)9781509053827

Recognition tasks in very low-resolution (VLR) images are more challenging than those in high-resolution (HR) due to lack of adequate discriminative information. Previous VLR and HR coupled learning scheme limits both the representation and discriminative ability of features. In this work, we propose a semi-coupled locality-constrained representation (SLR) approach to learn the discriminative representations and the mapping relationship between VLR and HR features simultaneously. Both VLR and HR local manifold geometries are coded during representation, while the learned mapping function improves the manifold consistency by transforming VLR features to HR ones. Finally, the resolutionrobust features are fed into a sparse representation based classifier (SRC) to predict the face labels. The proposed algorithm gives better performance than many state-of-the-art VLR recognition algorithms.

关键词： Dictionaries Face recognition Face Image resolution Manifolds Training Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Development of an attitude control system of a heavy-lift hexacopter using Elman recurrent neural networks

Development of an attitude control system of a heavy-lift he...

引用

international conference on Automation and Computing (ICAC)

作者： Benyamin Kusumoputro Herwin Suprijono Muhammad Ary Heryanto Bhakti Yudho Suprapto Dept. of Electrical Engineering Kampus Baru UI Depok Indonesia

Hexacopter is a type of multicopter that can be used to lift a heavy load, hence very convenient to be utilised in agricultural fields. As the consequence, however, the attitude control of this hexacopter is rather difficult compare with that of a quadcopter with four motors, due to gyroscopic effect of the additional motors and in its combination with the heavy loads. In this paper, we have developed a direct inverse controller system using an Elman neural networks for the attitude and altitude control of the hexacopter. Experiments are conducted using a flight data taken from a test-bed system. Results show that the attitude characteritics of the heavy-lift hexacopter can be controlled successfully, especially when an optimized Elman neural networks as the direct inverse controller system is utilized.

关键词： Control systems Biological neural networks Attitude control Neurons Recurrent neural networks Training learning systems

来源：评论

学校读者我要写书评

暂无评论

Accelerating learning to Rank via SVM with OpenCL and OpenMP on Heterogeneous Platforms

Accelerating Learning to Rank via SVM with OpenCL and OpenMP...

引用

international conference on Parallel and Distributed Systems (ICPADS)

作者： Huming Zhu Zheng Luo Yanfei Wu Pei Li Peng Zhang Shuiping Gou L.C. Jiao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi'an China Xidian University Xian Shaanxi CN

ISBN: (纸本)9781509053827

Support vector machine (SVM) is a popular algorithm for learning to rank, but the training speed of SVM is the bottleneck when dealing with large size data problems. Recently, heterogeneous computing platforms, such as graphics processing unit (GPU) and Many Integrated Core (MIC), have exhibited huge superiority in High Performance Computing domain. Open Computing Language (OpenCL) and Open Multi-Processing (OpenMP) are two popular parallel programming interface for different Heterogeneous Platforms. To resolve the speed problem of RSVM, comparison of the performance of different parallel programming models on different heterogeneous platforms is important. We designed OpenMPbased parallel learning to Rank SVM (PLRSVM) for multi-core CPU and MIC, and OpenCL-based PLRSVM for multi-core CPU, GPU and MIC. The experimental result shows the different performance between OpenMP based program and OpenCL based program. The OpenCL based program significantly speeds up training process of SVM and shows good portability on heterogeneous devices. The experiment also suggests that selection of suitable programming models according to the hardware platform and the structure of serial algorithm is an important step to acquire high performance of parallel algorithm.

关键词： Graphics processing units Support vector machines Microwave integrated circuits Training Parallel programming Algorithm design and analysis Acceleration

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226页 << < 181 182 183 184 185 186 187 188 189 190 > >>

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：