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

196 篇 会议
71 篇 期刊文献
4 册 图书

馆藏范围

271 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

150 篇 工学
- 126 篇 计算机科学与技术...
- 107 篇 软件工程
- 32 篇 生物工程
- 31 篇 生物医学工程（可授...
- 29 篇 信息与通信工程
- 22 篇 控制科学与工程
- 21 篇 光学工程
- 13 篇 电气工程
- 11 篇 电子科学与技术（可...
- 9 篇 仪器科学与技术
- 8 篇 化学工程与技术
- 6 篇 土木工程
- 6 篇 安全科学与工程
- 5 篇 网络空间安全
- 4 篇 建筑学
99 篇 理学
- 53 篇 数学
- 33 篇 生物学
- 31 篇 物理学
- 27 篇 统计学（可授理学、...
- 10 篇 系统科学
- 9 篇 化学
- 4 篇 地球物理学
34 篇 管理学
- 19 篇 图书情报与档案管...
- 15 篇 管理科学与工程(可...
- 10 篇 工商管理
21 篇 医学
- 20 篇 基础医学(可授医学...
- 20 篇 临床医学
- 15 篇 药学(可授医学、理...
8 篇 法学
- 8 篇 社会学
6 篇 农学
- 6 篇 作物学
3 篇 经济学
3 篇 教育学
1 篇 文学

主题

17 篇 accuracy
9 篇 feature extracti...
9 篇 machine learning
9 篇 training
8 篇 support vector m...
8 篇 artificial intel...
7 篇 computational mo...
7 篇 computer vision
6 篇 real-time system...
6 篇 machine learning...
5 篇 deep learning
5 篇 convolutional ne...
4 篇 learning systems
4 篇 optimization
4 篇 semantics
4 篇 python
3 篇 image enhancemen...
3 篇 reinforcement le...
3 篇 sensitivity
3 篇 automation

机构

5 篇 bmbf research hu...
5 篇 centre for cogni...
5 篇 dept. of electri...
4 篇 ai and machine l...
4 篇 data61 commonwea...
4 篇 chair of theoret...
4 篇 dept. of compute...
4 篇 dept. of machine...
3 篇 dept. of math an...
3 篇 department of co...
3 篇 department of co...
3 篇 dept. of electri...
3 篇 dept. of compute...
3 篇 dept. of electri...
3 篇 darmstadt
3 篇 australian insti...
3 篇 machine learning...
3 篇 dept. of compute...
3 篇 dept. of languag...
3 篇 machine learning...

作者

6 篇 shams mahmoud y.
5 篇 rafael f. schaef...
5 篇 horváth tamás
5 篇 wrobel stefan
5 篇 kersting kristia...
5 篇 h. vincent poor
5 篇 bouaynaya nidhal...
5 篇 rasool ghulam
4 篇 hong xudong
4 篇 demberg vera
4 篇 holger boche
4 篇 andrea grigoresc...
4 篇 mahmoud y. shams
3 篇 gagandeep kaur
3 篇 pareek piyush ku...
3 篇 bhatnagar roheet
3 篇 rutuja rajendra ...
3 篇 villani mattias
3 篇 govinda rajulu g...
3 篇 klaus-robert mül...

语言

262 篇 英文
9 篇 其他

检索条件"机构=Dept. of Computer Vision and Machine Learning"

共 271 条记录，以下是241-250 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：

Ensemble modeling with a constrained linear system of leave-one-out outputs

Ensemble modeling with a constrained linear system of leave-...

引用

18th European Symposium on Artificial Neural Networks, Computational Intelligence and machine learning, ESANN 2010

作者： Miche, Yoan Eirola, Emil Bas, Patrick Simula, Olli Jutten, Christian Lendasse, Amaury Verleysen, Michel Helsinki University of Technology Dept. of Information and Computer Science Konemiehentie 2 02015 TKK Finland Institut National Polytechnique de Grenoble Gipsa-Lab 961 rue de la Houille Blanche BP46 38402 Grenoble France Université Catholique de Louvain Machine Learning Group Place du Levant 3 B-1348-Louvain-la-Neuve Belgium

ISBN: (纸本)2930307102

This paper proposes a method for ensemble models using their Leave-One-Out output and solving a constrained linear system. By the use of the proposed method to create an ensemble of Locally Linear models, results on six different regression data sets are comparable to state-of-the-art methods such as Least-Squares Support Vector machines and Gaussian Processes, while being orders of magnitude faster.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Estimating vector fields using sparse basis field expansions

Estimating vector fields using sparse basis field expansions

引用

22nd Annual Conference on Neural Information Processing Systems, NIPS 2008

作者： Haufe, Stefan Nikulin, Vadim V. Ziehe, Andreas Müller, Klaus-Robert Nolte, Guido TU Berlin Dept. of Computer Science Machine Learning Laboratory Berlin Germany Berlin Germany Charité University Medicine Dept. of Neurology Campus Benjamin Franklin Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany

ISBN: (纸本)9781605609492

We introduce a novel framework for estimating vector fields using sparse basis field expansions (S-FLEX). The notion of basis fields, which are an extension of scalar basis functions, arises naturally in our framework from a rotational invariance requirement. We consider a regression setting as well as inverse problems. All variants discussed lead to second-order cone programming formulations. While our framework is generally applicable to any type of vector field, we focus in this paper on applying it to solving the EEG/MEG inverse problem. It is shown that significantly more precise and neurophysiologically more plausible location and shape estimates of cerebral current sources from EEG/MEG measurements become possible with our method when comparing to the state-of-the-art.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Search war: A game for improving web search

Search war: A game for improving web search

引用

ACM SIGKDD Workshop on Human Computation, HCOMP '09

作者： Law, Edith Von Ahn, Luis Mitchell, Tom Machine Learning Dept. Carnegie Mellon University 5000 Forbes Ave Pittsburgh PA 15217 United States Computer Science Dept. Carnegie Mellon University 5000 Forbes Ave Pittsburgh PA 15217 United States

We present a competitive online game called Search War, which collects data that is useful for improving Web search. Specifically, as a by product of gameplay, players will provide, for a given web page, an evaluation... 详细信息

ISBN: (纸本)9781605586724

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

learning invariances with stationary subspace analysis

Learning invariances with stationary subspace analysis

引用

2009 IEEE 12th International Conference on computer vision Workshops, ICCV Workshops 2009

作者： Meinecke, Frank C. Von Bünau, Paul Kawanabe, Motoaki Müller, Klaus-R. Machine Learning Group Dept. Computer Science TU Berlin Franklinstr. 28/29 10587 Berlin Germany Intelligent Data Analysis Group Fraunhofer FIRST.IDA Kekuléstr. 7 12489 Berlin Germany

ISBN: (纸本)9781424444427

Recently, a novel subspace decomposition method, termed 'Stationary Subspace Analysis' (SSA), has been proposed by Bünau et al. [10]. SSA aims to find a linear projection to a lower dimensional subspace such that the distribution of the projected data does not change over successive epochs or sub-datasets. We show that by modifying the loss function and the optimization procedure we can obtain an algorithm that is both faster and more accurate. We discuss the problem of indeterminacies and provide a lower bound on the number of epochs that is needed. Finally, we show in an experiment with simulated image patches, that SSA can be used favourably in invariance learning. ©2009 IEEE.

关键词： Invariance

来源：评论

学校读者我要写书评

暂无评论

IBM research TRECVID-2009 video retrieval system

IBM research TRECVID-2009 video retrieval system

引用

TREC Video Retrieval Evaluation, TRECVID 2009

作者： Natsev, Apostol Bao, Shenghua Chang, Jane Hill, Matthew Merler, Michele Smith, John R. Wang, Dong Xie, Lexing Yan, Rong Zhang, Yi IBM T. J. Watson Research Center Hawthorne NY United States IBM China Research Lab Beijing China IBM Software Group Cambridge MA United States Dept. of Computer Science Columbia University United States Machine Learning Dept. Carnegie Mellon Univ United States

In this paper, we describe the IBM Research system for indexing, analysis, and copy detection of video as applied to the TRECVID-2009 video retrieval benchmark. A. High-Level Concept Detection: This year, our focus was on global and local feature combination, automatic training data construction from web domain, and large-scale detection using Hadoop. 1. A_***_6: Baseline runs using 98 types of global features and 3 SVM learning methods;2. A_***2_5: Fusion of the 2 best models from 5 candidate models on global / local features;3. A_***_4: Fusion of all 5 candidate models on global / local features;4. A_***+08_3: Single best model from the 5 candidate models, plus the old models from 2008;5. C_***2+FlkBox_2: Combine A ***2 5 with automatic extracted training data from Flickr;6. A_***_1: Best overall run, assembled from best models for each concept using heldout performance. Overall, almost all the individual components can improve the mean average precision after fused with the baseline results. To summarize, we have the following observations from our evaluation results: 1) The global and local features are complementary to each other, and their fusion results outperform either individual types of features;2) The more features are combined, the better the performance, even with simple combination rules;3) The development data collected automatically from the web domain are shown to be useful on a number of the concepts, although its average performance is not comparable with manually selected training data, partially because of the large domain gap between web images and documentary video;B. Content-Based Copy Detection: The focus of our copy detection system this year was in fusing 4 types of complementary fingerprints: a temporal activity-based fingerprint, keyframe-based color correlogram and SIFTogram fingerprints, and an audio-based fingerprint. We also considered two approaches (meanand median-equalization)

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning with Weakly-Related Unlabeled Data: Towards better text categorization

Semi-supervised learning with Weakly-Related Unlabeled Data:...

引用

22nd Annual Conference on Neural Information Processing Systems, NIPS 2008

作者： Yang, Liu Jin, Rong Sukthankar, Rahul Machine Learning Dept. Carnegie Mellon University 5000 Forbes Avenue Pittsburgh PA 15213 United States Dept. of Computer Sci. and Eng. 3115 Engineering Building Michigan State University East Lansing MI 48824 United States Intel Research Pittsburgh Carnegie Mellon Univ. 4720 Forbes Avenue 410 Pittsburgh PA 15213 United States

ISBN: (纸本)9781605609492

The cluster assumption is exploited bymost semi-supervised learning (SSL)methods. However, if the unlabeled data is merely weakly related to the target classes, it becomes questionable whether driving the decision boundary to the low density regions of the unlabeled data will help the classification. In such case, the cluster assumption may not be valid;and consequently how to leverage this type of unlabeled data to enhance the classification accuracy becomes a challenge. We introduce "Semi-supervised learning with Weakly-Related Unlabeled Data" (SSLW), an inductive method that builds upon the maximum-margin approach, towards a better usage of weakly-related unlabeled information. Although the SSLW could improve a wide range of classification tasks, in this paper, we focus on text categorization with a small training pool. The key assumption behind this work is that, even with different topics, the word usage patterns across different corpora tends to be consistent. To this end, SSLW estimates the optimal wordcorrelation matrix that is consistent with both the co-occurrence information derived from the weakly-related unlabeled documents and the labeled documents. For empirical evaluation, we present a direct comparison with a number of stateof- the-art methods for inductive semi-supervised learning and text categorization. We show that SSLW results in a significant improvement in categorization accuracy, equipped with a small training set and an unlabeled resource that is weakly related to the test domain.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Experimental study on the effects of communication range on cooperative robotic search in complex environments

Experimental study on the effects of communication range on ...

引用

2009 2nd International Conference on Robot Communication and Coordination, RoboComm 2009

作者： Çaylrpunar, Ömer Gazi, Veysel Tavli, Bulent Cervera, Enric Witkowski, Ulf Penders, Jacques Dept. of Computer Engineering TOBB University of Economics and Technology Sögütözü Cad. No: 43 06560 Ankara Turkey Dept. of Electrical and Electronics Engineering TOBB University of Economics and Technology Sögütözü Cad. No: 43 06560 Ankara Turkey Dept. of Computer Science and Engineering Jaume-I University Campus Riu Sec 12071 Castelló Spain Heinz Nixdorf Institute University of Paderborn Fuerstenallee 1133102 Paderborn Germany Microsystems and Machine Vision Lab Sheffield Hallam University Pond Street Sheffield SI lWB United Kingdom

ISBN: (纸本)9789639799516

Communication has an important role in multirobot systems. It can facilitate cooperation, therefore, improve the performance of the system significantly. In this study we investigated the benefits of networked communication by experimentally evaluating the results of two search algorithms which are spiral search and informed random search. The experiments were performed in an experimental area containing obstacles and using e-puck robots where the communication ranges were "simulated" with the help of an overhead camera. Each robot was allowed to (i) keep an occupancy grid based local map of the environment containing also information about the cells it has visited and (ii) exchange this information with the other robots within its communication range. The effect of the size of communication range on the performance of the system defined as the time of completion of the search task (i.e, locating the target), was investigated.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Invariant common spatial patterns: Alleviating nonstationarities in Brain-computer Interfacing

Invariant common spatial patterns: Alleviating nonstationari...

引用

21st Annual Conference on Neural Information Processing Systems, NIPS 2007

作者： Blankertz, Benjamin Kawanabe, Motoaki Tomioka, Ryota Hohlefeld, Friederike U. Nikulin, Vadim Müller, Klaus-Robert TU Berlin Dept. of Computer Science Machine Learning Laboratory Berlin Germany Berlin Germany Dept. Mathematical Informatics IST University of Tokyo Japan School of Mind and Brain Berlin Germany Dept. of Neurology Campus Benjamin Franklin Charité University Medicine Berlin Germany

ISBN: (纸本)160560352X

Brain-computer Interfaces can suffer from a large variance of the subject conditions within and across sessions. For example vigilance fluctuations in the individual, variable task involvement, workload etc. alter the characteristics of EEG signals and thus challenge a stable BCI operation. In the present work we aim to define features based on a variant of the common spatial patterns (CSP) algorithm that are constructed invariant with respect to such nonstationarities. We enforce invariance properties by adding terms to the denominator of a Rayleigh coefficient representation of CSP such as disturbance covariance matrices from fluctuations in visual processing. In this manner physiological prior knowledge can be used to shape the classification engine for BCI. As a proof of concept we present a BCI classifier that is robust to changes in the level of parietal α-activity. In other words, the EEG decoding still works when there are lapses in vigilance.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Discovering cyclic causal models by independent components analysis

Discovering cyclic causal models by independent components a...

引用

作者： Lacerda, Gustavo Spirtes, Peter Ramsey, Joseph Hoyer, Patrik O. Machine Learning Department School of Computer Science Carnegie Mellon University Pittsburgh PA 15213 United States Department of Philosophy Carnegie Mellon University Pittsburgh PA 15213 United States Dept. of Computer Science University of Helsinki Helsinki Finland

ISBN: (纸本)0974903949

We generalize Shimizu et al's (2006) ICA-based approach for discovering linear non-Gaussian acyclic (LiNGAM) Structural Equation Models (SEMs) from causally sufficient, continuous-valued observational data. By relaxing the assumption that the generating SEM's graph is acyclic, we solve the more general problem of linear non-Gaussian (LiNG) SEM discovery. LiNG discovery algorithms output the distribution equivalence class of SEMs which, in the large sample limit, represents the population distribution. We apply a LiNG discovery algorithm to simulated data. Finally, we give sufficient conditions under which only one of the SEMs in the output class is "stable".

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Solving POMDPs from both sides: Growing dual parsimonious bounds

Solving POMDPs from both sides: Growing dual parsimonious bo...

引用

2008 AAAI Workshop

作者： Armstrong-Crews, Nicholas Gordon, Geoffrey Veloso, Manuela Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh PA 15213 United States Machine Learning Dept. Carnegie Mellon University 5000 Forbes Avenue Pittsburgh PA 15213 United States Computer Science Dept. Carnegie Mellon University 5000 Forbes Avenue Pittsburgh PA 15213 United States

ISBN: (纸本)9781577353690

Partially Observable Markov Decision Processes, or POMDPs, are useful for representing a variety of decision problems;unfortunately, solving for an optimal policy is computational intractable in general. In this paper, we present a set of novel search techniques for solving POMDPs approximately. We build on previous heuristic search and point-based algorithms, but improve upon them in several ways: we introduce an efficient method for approximating the convex hull of the upper bound, we expose embedded finite Markov structure in each bound, and we show how to prune aggressively while still maintaining convergence. The net result is a more targeted growth of the bound representations, leading to lower overall runtime and storage. We synthesize these contributions into a novel algorithm, which we call AAA-POMDP (Appropriately Acronymmed Algorithm). We describe its theoretical properties, including computational efficiency, and examine its performance on on standard benchmark problems from the literature. On these problems, our algorithms exhibit competitive or superior performance when compared to previous methods. © 2008, Association for the Advancement of Artificial Intelligence.

关键词： Computational efficiency

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28页 << < 19 20 21 22 23 24 25 26 27 28 > >>

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：