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

8,592 篇 会议
4,563 篇 期刊文献
6 篇 学位论文
2 篇 资讯
1 册 图书

馆藏范围

13,164 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

12,749 篇 工学
- 11,981 篇 计算机科学与技术...
- 9,578 篇 软件工程
- 1,724 篇 生物工程
- 1,627 篇 信息与通信工程
- 1,454 篇 控制科学与工程
- 1,179 篇 电气工程
- 588 篇 生物医学工程（可授...
- 351 篇 机械工程
- 340 篇 光学工程
- 320 篇 电子科学与技术（可...
- 303 篇 化学工程与技术
- 232 篇 安全科学与工程
- 201 篇 动力工程及工程热...
- 176 篇 仪器科学与技术
- 145 篇 土木工程
5,629 篇 理学
- 3,384 篇 数学
- 1,867 篇 生物学
- 1,295 篇 统计学（可授理学、...
- 791 篇 物理学
- 670 篇 系统科学
- 239 篇 化学
2,175 篇 管理学
- 1,362 篇 图书情报与档案管...
- 875 篇 管理科学与工程(可...
- 439 篇 工商管理
627 篇 医学
- 514 篇 临床医学
- 476 篇 基础医学(可授医学...
- 307 篇 药学(可授医学、理...
338 篇 法学
- 321 篇 社会学
188 篇 教育学
- 180 篇 教育学
158 篇 经济学
- 153 篇 应用经济学
135 篇 农学
86 篇 文学
15 篇 艺术学
13 篇 军事学
3 篇 哲学
1 篇 历史学

主题

13,164 篇 learning algorit...
98 篇 neural networks
70 篇 learning
56 篇 machine learning
40 篇 neural network
36 篇 algorithms
27 篇 learning (artifi...
25 篇 artificial intel...
24 篇 learning systems
24 篇 iterative method...
24 篇 optimization
24 篇 game theory
24 篇 classification
21 篇 reinforcement le...
21 篇 classifiers
20 篇 dataset
20 篇 artificial neura...
19 篇 training
18 篇 genetic algorith...
18 篇 iterative learni...

机构

37 篇 university of ca...
37 篇 stanford univers...
32 篇 carnegie mellon ...
30 篇 google research ...
29 篇 uc berkeley unit...
27 篇 carnegie mellon ...
25 篇 columbia univers...
24 篇 mit united state...
23 篇 university colle...
23 篇 microsoft resear...
23 篇 google research
22 篇 massachusetts in...
22 篇 deepmind united ...
21 篇 tsinghua univers...
21 篇 princeton univer...
20 篇 cornell universi...
19 篇 deepmind
19 篇 university of pe...
19 篇 stanford univ st...
18 篇 mit cambridge ma...

作者

22 篇 mohri mehryar
21 篇 levine sergey
21 篇 tao dacheng
20 篇 liu yang
15 篇 moran shay
14 篇 zhou zhi-hua
14 篇 krause andreas
14 篇 jin rong
14 篇 mansour yishay
14 篇 wang wei
14 篇 precup doina
13 篇 hanneke steve
12 篇 liu tongliang
12 篇 bengio yoshua
11 篇 yang qiang
11 篇 pontil massimili...
11 篇 daumé hal
11 篇 sun wen
11 篇 silver david
11 篇 diakonikolas ili...

语言

11,666 篇 英文
1,349 篇 其他
109 篇 中文
17 篇 法文
14 篇 土耳其文
7 篇 德文
6 篇 日文
5 篇 西班牙文
5 篇 朝鲜文
4 篇 俄文
3 篇 葡萄牙文
1 篇 乌克兰文

检索条件"主题词=Learning algorithms"

共 13164 条记录，以下是4301-4310 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：

Improving Approximate Logic Neuron Model by Means of a Novel learning Algorithm 16th

Improving Approximate Logic Neuron Model by Means of a Novel...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Zhao, Jiajun Dong, Minhui Tang, Cheng Ji, Junkai He, Ying College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Faculty of Engineering University of Toyama Toyama-shi930-8555 Japan

ISBN: (纸本)9783030607982

Inspired by the dynamic dendritic architecture of biological neurons, the approximate logic neuron model (ALNM) is a novel model recently proposed by us. ALNM owns four layers, namely, the synaptic layer, the dendritic layer, the membrane layer, and the cell body. Through neural pruning function, the model can omit useless synapses and unnecessary branches of dendrites after the training process. In other words, it will form a unique and simplified dendritic structure for each particular classification task. Further, the simplified dendritic structure can be completely substituted by logic circuits, which makes ALNM be capable of running in hardware. However, although it has satisfactory performances to solve classification problems, it still suffers from some disadvantages owing to its learning algorithm, named batch gradient descent (BGD) algorithm. It is because that, using all the training data for each iteration is time-consuming and it is unsuitable for large scale problems. In addition, BGD cannot adaptively adjust the learning rate during the whole training process, which will converge slowly in the neighborhood of saddle points, and oscillate in the steep region of gradient space. To settle the above issues, we propose a novel stochastic adaptive gradient descent (SAGD) algorithm, which uses stochastic gradient descent information and adaptively adjusts the learning rate, to improve the classification performances of ALNM. In our experiments, ALNM trained by the new algorithm is evaluated on three benchmark classification datasets, and experimental results demonstrate that it performs significantly better than the original model in terms of accuracy and convergence rate. © 2020, Springer Nature Switzerland AG.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-category Classification Problem Oriented Subsampling-Based Active learning Method 2

Multi-category Classification Problem Oriented Subsampling-B...

引用

2nd International Conference on Artificial Intelligence and Computer Science, AICS 2020

作者： Shi, Wei Feng, Yanghe Cheng, Guangquan Liu, Shixuan Liu, Zhong College of Systems Engineering National University of Defense Technology Changsha China

Traditional active learning methods have achieved gratifying results in the classification tasks of less categories such as binary classification, the application research of active learning in the field of big data problems still faces enormous challenges. Since many active learning query strategies need to perform matrix inversion, the amount of calculation increases exponentially with the increase of the scale of the problem, it is difficult to apply these active learning methods in large scale multi-category data classification task. In order to solve this problem, this paper designed a subsampling-based active learning model, and integrate unsupervised clustering algorithm with traditional active learning method, then conducted experiments on Binary Alphadigits and OMNIGLOT data sets. This paper compares the performance of five traditional active learning algorithms using this subsampling method, namely random sampling, uncertainty sampling, query-by-committee, density weighting and learning-based active learning. Through comparative experiments, the feasibility of active learning based on subsampling for solving the multi-category classification problem is verified, and it is found that the subsampling-based method can break the limitations of traditional active learning methods that cannot deal with large-scale data classification. © Published under licence by IOP Publishing Ltd.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Online Signature Verification Using Deep learning and Feature Representation Using Legendre Polynomial Coefficients 4th

引用

4th International Conference on Advanced Machine learning Technologies and Applications, AMLTA 2019

作者： Hefny, Amr Moustafa, Mohamed Mathematics Department Faculty of Science Cairo University Giza12613 Egypt Computer and Systems Engineering Department Faculty of Engineering Ain Shams University Cairo Egypt

ISBN: (纸本)9783030141172

Handwritten signing are one of the most popular behavioral biometrics. They are widely accepted for verification purposes, such as authenticating legal documents and financial contracts. In this paper, Legendre polynomials coefficients are used as features to model the signatures. The classifier used in this paper is deep feedforward neural network and the deep learning algorithm is stochastic gradient descent with momentum. The experimental results show better Equal Error Rate reduction and accuracy enhancement on SigComp2011 Dataset presented within ICDAR 2011 in comparison with state-of-the-art methods. © 2020, Springer Nature Switzerland AG.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning with the Classical Q-learning Algorithm for Optimizing Single Intersection Performance

Reinforcement Learning with the Classical Q-Learning Algorit...

引用

2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Rosyidi, M. Bismantoko, Sahid Widodo, Tri Agency for the Assessment and Application of Technology Center of Technology for System and Infrastructure of Transportation Tangerang Selatan Indonesia

ISBN: (纸本)9781728196756

Many factors causing the issue of the land transportation like intersections problems. In cities where the volume of vehicles passing through an intersection is so large that sometimes a vehicle can pass through an intersection after two or three red lights. The length of the queue at each leg of the intersection can cause the average delay time to be large. In this research, optimizing the performance of a single intersection is an attempt to minimize the average delay time at a single intersection using the classical Q-learning algorithm. The data used in this study were obtained from the local government of Pekalongan City. The results of this study indicate that minimizing the average delay time will also affect the traffic light time cycle setting, which causes the queue length at the intersection to decrease as well, in this study the parameter value used for the learning rate is 0.5, and the average delay time decreased by 2.96 seconds. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal Terminal Iterative learning Control for the Parking Control System of Maglev Train 4

Optimal Terminal Iterative Learning Control for the Parking ...

引用

2020 4th International Conference on Traffic Engineering and Transportation System, ICTETS 2020

作者： Zhang, Pengju School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

This paper analyzes the parking process of maglev trains, establishes the corresponding mathematical model, based on the method of terminal iterative learning control(TILC), uses the stopping position error in the previous braking process to update the current control curve. In this paper, we select the initial braking position, initial speed or braking force or a combination thereof as the control input, and formulate the corresponding learning law. Finally, a line is simulated, and the traditional TILC method and the optimal TILC method are compared through simulation experiments, which verify that the latter has a faster convergence speed. © Published under licence by IOP Publishing Ltd.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Phony news detection using machine learning and deep-learning techniques 9

Phony news detection using machine learning and deep-learnin...

引用

9th International Conference on System Modeling and Advancement in Research Trends, SMART 2020

作者： Garg, Sonal Sharma, Dilip Kumar GLA University Mathura India

ISBN: (纸本)9781728189086

The proliferation of misleading news stories on social-media raised a big challenge due to its potential to create an adverse impact on human-being. Existing lexico-syntactic features are unable to detect counterfeit news. Most of the state of art algorithms used small datasets containing a limited number of the training dataset. In this paper, we evaluate our framework on the LIAR dataset by applying machine learning and advanced deep learning techniques. LIAR is a predominant dataset consist of 12, 836 short news collected from different sources, including social media. The proposed framework uses POS (part of speech) tagging information and Glove Embedding. The result shows the superiority in terms of accuracy in comparison to the existing state of the art algorithm. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Classification of intrusion detection system based on machine learning 2nd

Classification of intrusion detection system based on machin...

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： Chuang, Hsiu-Min Huang, Hui-Ying Liu, Fanpyn Tsai, Chung-Hsien Department of Computer Science and Information Engineering Chung Cheng Institute of Technology National Defense University Taoyuan Taiwan

ISBN: (纸本)9789811561122

In order to detect abnormal network behaviors early, it is common to build an intrusion detection system (IDS) by recording logs and analyzing active processes on the host. In this way, mining host behavior patterns from massive logs plays an important role in identifying anomalies in order to provide corresponding courses of action, such as blocking or tracking threats. Because of the ever-changing nature of cyber-attacks, it is critical to identify previously unknown threats. In this paper, we propose the hierarchical multi-class classifier (HMC) approach to intrusion detection, which combines multiple binary classifiers into a hierarchy architecture. In addition, we extract the characteristics of data distribution using a k-means algorithm to append new features to the original NSL-KDD public dataset to use as our experimental dataset. The experimental results show that our HMC approach outperforms other classifiers to reach 78% of F1-measure. This paper provides a preliminary research direction for detecting unseen and new types of abnormal activities in IDS. For future work, we will consider the feature representation by deep learning algorithms to improve their performance in practical applications. © Springer Nature Singapore Pte Ltd 2020.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Personalised meta-learning for human activity recognition with few-data 40th

Personalised meta-learning for human activity recognition wi...

引用

40th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, AI 2020

作者： Wijekoon, Anjana Wiratunga, Nirmalie School of Computing Robert Gordon University AberdeenAB10 7GJ United Kingdom

ISBN: (纸本)9783030637989

State-of-the-art methods of Human Activity Recognition (HAR) rely on a considerable amount of labelled data to train deep architectures. This becomes prohibitive when tasked with creating models that are sensitive to personal nuances in human movement, explicitly present when performing exercises and when it is infeasible to collect training data to cover the whole target population. Accordingly, learning personalised models with few data remains an open challenge in HAR research. We present a meta-learning methodology for learning-to-learn personalised models for HAR;with the expectation that the end-user only need to provide a few labelled data. These personalised HAR models benefit from the rapid adaptation of a generic meta-model using provided few end-user data. We implement the personalised meta-learning methodology with two algorithms, Personalised MAML and Personalised Relation Networks. A comparative study shows significant performance improvements against state-of-the-art deep learning algorithms and other personalisation algorithms in multiple HAR domains. Also, we show how personalisation improved meta-model training, to learn a generic meta-model suited for a wider population while using a shallow parametric model. © Springer Nature Switzerland AG 2020.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep learning neural networks in fuzzy modeling 13

Deep learning neural networks in fuzzy modeling

引用

13th International Scientific and Technical Conference on Applied Mechanics and Systems Dynamics, AMSD 2019

作者： Sotvoldiev, D. Muhamediyeva, D.T. Juraev, Z. Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Amir Temur street 108 Tashkent100200 Uzbekistan

Deep learning neural networks have achieved remarkable success in various fields of application of artificial intelligence. This technology, which grew out of studies of artificial neural networks, has shown superior performance compared to other machine learning algorithms in areas such as image and voice recognition, natural language processing, and others. The use of deep learning neural networks in the construction of a fuzzy model is proposed. © Published under licence by IOP Publishing Ltd.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-class Image Classification Using Deep learning Algorithm 4

Multi-class Image Classification Using Deep Learning Algorit...

引用

4th International Conference on Advanced Technology and Applied Sciences, ICaTAS 2019

作者： Ezat, W.A. Dessouky, M.M. Ismail, N.A. Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf Menoufia Egypt

Classifying images is a complex problem in the field of computer vision. The deep learning algorithm is a computerized model simulates the human brain functions and operations. Training the deep learning model is a costly process in machine resources and time. Investigating the performance of the deep learning algorithm is mostly needed. The convolutional neural network (CNN) is most commonly used to build a structure of the deep learning models. In this paper convolutional neural network (CNN) model pre-trained on Image-Net is used for classification of images of the PASCAL VOC 2007 data-set. The transfer learning approach is used to improve the performance of the deep learning CNN model where classification works fairly well with the smallest amount of computation time and fewer machine resources. The behavior of the Deep learning CNN model is studied and the performance has been measured. The obtained results are compared with the obtained test results from the Super-vector coding of local image descriptors method, SVM method, and Region Ranking SVM method, which tested with the PASCAL VOC 2007 data-set. The final results evaluate the deep learning algorithm as a state-of-the-art method for an image classification task. © Published under licence by IOP Publishing Ltd.

关键词： learning algorithms

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500页 << < 427 428 429 430 431 432 433 434 435 436 > >>

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：