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

775 篇 会议
3 篇 期刊文献
2 册 图书

馆藏范围

780 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

597 篇 工学
- 561 篇 计算机科学与技术...
- 284 篇 电气工程
- 139 篇 软件工程
- 75 篇 信息与通信工程
- 31 篇 控制科学与工程
- 23 篇 生物工程
- 22 篇 生物医学工程（可授...
- 11 篇 机械工程
- 9 篇 交通运输工程
- 8 篇 安全科学与工程
- 7 篇 仪器科学与技术
- 6 篇 测绘科学与技术
- 6 篇 网络空间安全
- 5 篇 光学工程
- 5 篇 动力工程及工程热...
56 篇 管理学
- 34 篇 管理科学与工程(可...
- 28 篇 图书情报与档案管...
- 13 篇 工商管理
51 篇 理学
- 24 篇 生物学
- 22 篇 数学
- 12 篇 统计学（可授理学、...
- 11 篇 系统科学
- 9 篇 物理学
- 4 篇 化学
33 篇 医学
- 33 篇 临床医学
- 6 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
13 篇 教育学
- 13 篇 教育学
8 篇 法学
- 6 篇 社会学
5 篇 经济学
- 5 篇 应用经济学
2 篇 文学
2 篇 农学

主题

297 篇 machine learning
126 篇 training
87 篇 feature extracti...
66 篇 deep learning
45 篇 data models
43 篇 neural networks
39 篇 machine learning...
38 篇 computational mo...
37 篇 predictive model...
34 篇 support vector m...
30 篇 visualization
27 篇 training data
24 篇 data mining
23 篇 semantics
22 篇 three-dimensiona...
21 篇 cameras
20 篇 conferences
20 篇 computer vision
19 篇 image segmentati...
19 篇 optimization

机构

4 篇 ecole polytech f...
4 篇 univ edinburgh e...
4 篇 queen mary univ ...
4 篇 hunan univ coll ...
3 篇 carnegie mellon ...
3 篇 yunnan univ sch ...
3 篇 univ fed sao car...
3 篇 yonsei univ
3 篇 school of softwa...
3 篇 carnegie mellon ...
3 篇 sun yat sen univ...
3 篇 univ calgary hot...
3 篇 queens univ belf...
3 篇 idiap res inst m...
2 篇 johns hopkins un...
2 篇 school of comput...
2 篇 hong kong polyte...
2 篇 jsc russian rail...
2 篇 georgia inst tec...
2 篇 inesc tec porto

作者

5 篇 wang yingxu
4 篇 wang guojun
3 篇 li xin
3 篇 yang yun
3 篇 yun yang
3 篇 ghasemzadeh hass...
3 篇 gupta sandeep k....
3 篇 sandeep k. s. gu...
3 篇 banerjee ayan
3 篇 shayea ibraheem
3 篇 ibraheem shayea
3 篇 fleuret francois
3 篇 ayan banerjee
3 篇 nicoletti maria ...
3 篇 carvalho rommel ...
3 篇 ramin fallahzade...
3 篇 rokni seyed ali
3 篇 carvalho ricardo...
3 篇 hassan ghasemzad...
2 篇 pankaj dikshit

语言

777 篇 英文
3 篇 其他

检索条件"任意字段=16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017"

共 780 条记录，以下是1-10 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：

Proceedings - 16th ieee international conference on machine learning and applications, icmla 2017

Proceedings - 16th IEEE International Conference on Machine ...

引用

16th ieee international conference on machine learning and applications, icmla 2017

ISBN: (纸本)9781538614174

the proceedings contain 197 papers. the topics discussed include: anytime exploitation of stragglers in synchronous stochastic gradient descent;an evolutionary learning approach to self-configuring image pipelines in the context of carbon fiber fault detection;learning to coordinate with deep reinforcement learning in doubles pong game;anomaly prediction based on k-means clustering for memory-constrained embedded devices;clustering distributed short time series with dense patterns;attribute assisted interpretation confidence classification using machine learning;predictive modelling strategies to understand heterogeneous manifestations of asthma in early life;home appliance energy disaggregation using low frequency data and machine learning classifiers;on the impacts of noise from group-based label collection for visual classification;learning robust video synchronization without annotations;machine learning in appearance-based robot self-localization;learning antecedent structures for event coreference resolution;automatic generation and recommendation for API mashups;an evolutionary learning approach to self-configuring image pipelines in the context of carbon fiber fault detection;and machine learning approach to detecting sensor data modification intrusions in WBANs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Composition for Continual learning in Application of Cyberattack Detection 16th

Data Composition for Continual Learning in Application of Cy...

引用

16th international conference on Social Networks Analysis and Mining

作者： Lian, Jiayi Liu, Xueying Choi, Kevin Veeramani, Balaji Murli, Sathvik Hu, Alison Freeman, Laura Bowen, Edward Deng, Xinwei Virginia Tech Dept Stat Falls Church VA 22043 USA Deloitte & Touche AI Ctr Excellence New York CA USA

ISBN: (纸本)9783031785535;9783031785542

Continual learning (CL) focuses on enabling machine learning algorithms to learn from a series of tasks without forgetting previously acquired knowledge. the use of continual learning has not been widely explored in cybersecurity and network safety applications, partially due to the lack of proper datasets. Besides, the benchmark datasets used in CL methods are often relatively restrictive in terms of data distribution shift among the tasks. In this work, we present a CL benchmark framework to construct datasets for CL in cybersecurity applications. For the cybersecurity applications, the proposed framework can generate datasets for CL under distribution shifts in data inputs (e.g., features of internet traffic flow), distribution shifts in data output (e.g., intrusion types), and distribution shifts in both data inputs and outputs, respectively. Moreover, we propose several distance-based and model-based metrics tometiculously quantify the magnitude of distribution shift between datasets of the tasks. We elaborate the construction of benchmark datasets and evaluate the quality of the constructed datasets by applying several existing CL methods and investigating their performance.

关键词： Cybersecurity Continual learning Distribution shift Network safety

来源：评论

学校读者我要写书评

暂无评论

Attribute Assisted Interpretation Confidence Classification Using machine learning 16

Attribute Assisted Interpretation Confidence Classification ...

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Weinzierl, Wolfgang Schlumberger Integrated Solut Schlumberger Copenhagen Denmark

ISBN: (纸本)9781538614174

An attribute assisted classification deriving estimates of interpretation confidence was performed. Instantaneous and coherency attributes were used in a supervised followed by an unsupervised classification resulting in an error envelope of the interpretation. In an initial approximation, confidence weights for a signal and background response are estimated using support vector machine learning. Subsequently, a weighted discrimination based on several coherency attributes using self-organizing maps is obtained. the resulting quantization is used as additional input and constraint in a final probability assessment of signal confidence using instantaneous attributes in support vector machine learning. the additional input in the form of quantization vectors and possible reduction in dimensionality of the input attribute vector space, allows to combine highly non-linear correlations in a multivariate discrimination. the trained classification is used to assign signal confidence probabilities to an interpreted seismic horizon. the proposed methodology is applied to an onshore data set from Wyoming, USA, revealing how single-and multi-trace attributes can be used to quantitatively assess the uncertainty of an interpretation often lost during project maturation.

关键词： Self-Organizing Maps Interpretation Uncertainty Support Vector machine learning

来源：评论

学校读者我要写书评

暂无评论

Time-Sensitive Adaptation of Regularization Strength of Recurrent Neural Networks for Accurate learning 16

Time-Sensitive Adaptation of Regularization Strength of Recu...

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Kim, Kangil Konkuk Univ Seoul South Korea

ISBN: (纸本)9781538614174

Regularization is an important issue for neural networks because of strong expression power causing overfitting to data. A regularization method is to penalize cost functions by activation-based penalty. In its applications to recurrent neural networks, the method usually assigns penalty uniformly distributed over time steps. However, required strength for recurrent networks differs by time steps. In this paper we propose a new activation-based penalty function varying its strength over time steps in recurrent neural networks. To verify its impact, we conducted practical experiments to predict the power consumption of home appliances. In the results, the proposed method reduced training errors and maintained validation and test errors, which implies the improvement of forecasting ability. In sensitivity analysis, the method restricted sudden decrease of impact of early time steps to the cost.

关键词： recurrent neural network long-short term memory regularization time-varying impact penalization

来源：评论

学校读者我要写书评

暂无评论

Rank learning by Ordinal Gerrymandering 16

Rank Learning by Ordinal Gerrymandering

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Fenu, Stefano Rozell, Chris Georgia Inst Technol Atlanta GA 30332 USA

ISBN: (纸本)9781538614174

Many applications, from ordering search engine results to medical triage, rely on learning to accurately rank a set of objects by combining a given collection of ranking or preference functions. We propose a technique for rank-learning using a boosting approach which merges accurate regions of poor-quality metrics into a single accurate metric. We show an improvement in accuracy for general similarity-ranking tasks across a variety of benchmark datasets and apply this technique to the prediction of software bug severity and resolution time from error report text, showing a significant improvement in bug triage accuracy over the state of the art.

关键词： ranking machine learning boosting computer applications

来源：评论

学校读者我要写书评

暂无评论

machine learning Methods Used in Evaluations of Secure Biometric System Components 16

Machine Learning Methods Used in Evaluations of Secure Biome...

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Arslan, Bilgehan Ulker, Mehtap Sagiroglu, Seref Gazi Univ Comp Engn Ankara Turkey

ISBN: (纸本)9781538614174

this paper provides a comprehensive overview of theories, methodologies, techniques, standards and frameworks of biometric systems. the studies conducted between 2007-2017 are examined in order to ensure the security of the equipment used in a biometric system, to secure the characteristic feature extraction, to provide secure data storage in the biometric database, to maintain transmission channels used in biometric applications from vulnerabilities, and to ensure the correctness of the results obtained from intelligent decision mechanism. machine learning techniques used to detect and protect existing attacks are analyzed, obtained results are shared and recommendations are made in the last part of the study.

关键词： Biometric attack machine learning template security identification recognition data acquisition standard attack security

来源：评论

学校读者我要写书评

暂无评论

Automated Patent Classification Using Word Embedding 16

Automated Patent Classification Using Word Embedding

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Grawe, Mattyws F. Martins, Claudia A. Bonfante, Andreia G. Univ Fed Mato Grosso Inst Comp Cuiaba Brazil

ISBN: (纸本)9781538614174

Patent classification is the task of assign a special code to a patent, where the assigned code is used to group patents with similar subject into a same category. this paper presents a patent categorization method based on word embedding and long short term memory network to classify patents down to the subgroup IPC level. the experimental results indicate that our classification method achieve 63% accuracy at the subgroup level.

关键词： Automated Classification Patent Word Embedding Deep learning

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning based surface inspection by synthetizing artificial defects 16

Supervised machine learning based surface inspection by synt...

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Haselmann, M. Gruber, D. P. Polymer Competence Ctr Leoben GmbH Opt & Hapt Mat Characterist Leoben Austria

ISBN: (纸本)9781538614174

the preparation of labeled training data for supervised machine learning methods involves a lot of effort. Regarding surface inspection tasks, this endeavor is often not economically reasonable. In this paper, an artificial defect synthetization algorithm based on a multistep stochastic process is proposed. It adds defects to fault-free surface images, which can be used for supervised machine learning. By this means a deep convolutional neural network has been trained, achieving a detection rate of 94% of occurring real defects on the presented test surface.

关键词： inspection surface images image synthetization artificial defects supervised machine learning convolutional neural nets deep learning

来源：评论

学校读者我要写书评

暂无评论

Sequential Inverse Approximation of a Regularized Sample Covariance Matrix 16

Sequential Inverse Approximation of a Regularized Sample Cov...

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Lancewicki, Tomer EBay Inc 625 6th Ave New York NY USA

ISBN: (纸本)9781538614174

One of the goals in scaling sequential machine learning methods pertains to dealing with high-dimensional data spaces. A key related challenge is that many methods heavily depend on obtaining the inverse covariance matrix of the data. It is well known that covariance matrix estimation is problematic when the number of observations is relatively small compared to the number of variables. A common way to tackle this problem is through the use of a shrinkage estimator that offers a compromise between the sample covariance matrix and a well-conditioned matrix, with the aim of minimizing the mean-squared error. We derived sequential update rules to approximate the inverse shrinkage estimator of the covariance matrix. the approach paves the way for improved large-scale machine learning methods that involve sequential updates.

关键词： Covariance matrices Manganese Computer architecture Estimation Complexity theory learning systems Training

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep learning Methods Applied on Load Forecasting 16

A Review of Deep Learning Methods Applied on Load Forecastin...

引用

16th ieee international conference on machine learning and applications (icmla)

作者： Almalaq, Abdulaziz Edwards, George Univ Denver Dept Elect & Comp Engn Denver CO 80210 USA

ISBN: (纸本)9781538614174

the utility industry has invested widely in smart grid (SG) over the past decade. they considered it the future electrical grid while the information and electricity are delivered in two-way flow. SG has many Artificial Intelligence (AI) applications such as Artificial Neural Network (ANN), machine learning (ML) and Deep learning (DL). Recently, DL has been a hot topic for AI applications in many fields such as time series load forecasting. this paper introduces the common algorithms of DL in the literature applied to load forecasting problems in the SG and power systems. the intention of this survey is to explore the different applications of DL that are used in the power systems and smart grid load forecasting. In addition, it compares the accuracy results RMSE and MAE for the reviewed applications and shows the use of convolutional neural network CNN with k-means algorithm had a great percentage of reduction in terms of RMSE.

关键词： Artificial neural networks Forecasting learning (artificial intelligence) machine learning Smart grids

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78页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：