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

2,644 篇 会议
61 篇 期刊文献
38 册 图书
3 篇 学位论文

馆藏范围

2,746 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,237 篇 工学
- 1,991 篇 计算机科学与技术...
- 779 篇 软件工程
- 488 篇 电气工程
- 437 篇 信息与通信工程
- 174 篇 控制科学与工程
- 167 篇 生物工程
- 119 篇 生物医学工程（可授...
- 56 篇 仪器科学与技术
- 55 篇 化学工程与技术
- 50 篇 安全科学与工程
- 46 篇 机械工程
- 42 篇 电子科学与技术（可...
- 38 篇 光学工程
- 26 篇 动力工程及工程热...
537 篇 理学
- 279 篇 数学
- 187 篇 生物学
- 114 篇 物理学
- 108 篇 系统科学
- 108 篇 统计学（可授理学、...
- 54 篇 化学
266 篇 管理学
- 141 篇 图书情报与档案管...
- 136 篇 管理科学与工程(可...
- 64 篇 工商管理
146 篇 医学
- 122 篇 临床医学
- 56 篇 基础医学(可授医学...
- 36 篇 药学(可授医学、理...
- 27 篇 特种医学
- 25 篇 医学技术（可授医学...
41 篇 法学
- 33 篇 社会学
35 篇 教育学
- 28 篇 教育学
22 篇 经济学
22 篇 农学
8 篇 文学
5 篇 艺术学
1 篇 军事学

主题

897 篇 machine learning
218 篇 deep learning
123 篇 feature extracti...
106 篇 training
103 篇 machine learning...
85 篇 classification
72 篇 cloud computing
70 篇 support vector m...
70 篇 neural networks
62 篇 big data
60 篇 data mining
60 篇 computational mo...
53 篇 artificial intel...
49 篇 sentiment analys...
45 篇 predictive model...
43 篇 intrusion detect...
40 篇 reinforcement le...
38 篇 data models
35 篇 neural network
34 篇 internet of thin...

机构

12 篇 univ chinese aca...
11 篇 institute of mac...
7 篇 school of comput...
7 篇 fudan university
7 篇 school of electr...
7 篇 guangxi academy ...
6 篇 università di ca...
6 篇 infn sezione di ...
6 篇 north-west unive...
6 篇 in2p3 lpc campus...
6 篇 institut univers...
6 篇 national centre ...
6 篇 tno technical sc...
6 篇 université de st...
6 篇 nikhef national ...
6 篇 university würzb...
6 篇 université de ha...
6 篇 university of jo...
6 篇 university moham...
6 篇 astrocent nicola...

作者

14 篇 qin xiao
8 篇 yuan chang-an
8 篇 huang de-shuang
7 篇 chen hao
7 篇 yuan changan
7 篇 wu hongjie
7 篇 zhao xingming
6 篇 chen a.
6 篇 benoit d.m.
6 篇 ferrara g.
6 篇 ardid m.
6 篇 calvo d.
6 篇 gagliardini s.
6 篇 eddymaoui a.
6 篇 kulikovskiy v.
6 篇 labalme m.
6 篇 gal t.
6 篇 bozza c.
6 篇 khatun a.
6 篇 kalekin o.

语言

2,639 篇 英文
69 篇 中文
39 篇 其他

检索条件"任意字段=2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017"

共 2746 条记录，以下是331-340 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：

Stroke Based Posterior Attention for Online Handwritten Mathematical Expression Recognition 25

Stroke Based Posterior Attention for Online Handwritten Math...

引用

25th international conference on Pattern Recognition (ICPR)

作者： Wu, Changjie Wang, Qing Zhang, Jianshu Du, Jun Wang, Jiaming Wu, Jiajia Hu, Jinshui Univ Sci & Technol China NEL SILP Hefei Anhui Peoples R China iFLYTEK CO LTD AI Res Hefei Anhui Peoples R China

ISBN: (纸本)9781728188089

Recently, many researches propose to employ attention based encoder-decoder models to convert a sequence of trajectory points into a LaTeX string for online handwritten mathematical expression recognition (OHMER), and the recognition performance of these models critically relies on the accuracy of the attention. In this paper, unlike previous methods which basically employ a soft attention model, we propose to employ a posterior attention model, which modifies the attention probabilities after observing the output probabilities generated by the soft attention model. In order to further improve the posterior attention mechanism, we propose a stroke average pooling layer to aggregate point-level features obtained from the encoder into stroke-level features. We argue that posterior attention is better to be implemented on stroke-level features than point-level features as the output probabilities generated by stroke is more convincing than generated by point, and we prove that through experimental analysis. Validated on the CROHME competition task, we demonstrate that stroke based posterior attention achieves expression recognition rates of 54.26% on CROHME 2014 and 51.75% on CROHME 2016. According to attention visualization analysis, we empirically demonstrate that the posterior attention mechanism can achieve better alignment accuracy than the soft attention mechanism.

关键词： Posterior attention Stroke Online handwritten mathematical expression recognition Sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning for Job Scheduling on Cluster 30th

Deep Reinforcement Learning for Job Scheduling on Cluster

引用

30th international conference on Artificial Neural Networks (ICANN)

作者： Yao, Zhenjie Chen, Lan Zhang, He Chinese Acad Sci Inst Microelect Beijing Peoples R China Beijing Key Lab Three Dimens & Nanometer Integrat Beijing Peoples R China Purple Mt Lab Networking Commun & Secur Nanjing Peoples R China

ISBN: (纸本)9783030863807;9783030863791

Job scheduling is a key function of cluster computing. Efficient job scheduling can improve hardware resource utilization and promote the execution efficiency of jobs. Conventional scheduling work is dominated by heuristic algorithms. The scheduling efficiency of the heuristic algorithm is not optimal. In this paper, we improved the deep reinforcement learning algorithm for the cluster scheduling, which named DeepCM. Test results on the simulation data shows that the DeepCM is capable of improving the performance for job scheduling on the cluster. The slowdown could be improved from 2.248 to 2.235 in a environment of 3 machines. The fusion of internal baseline and external baseline could reduce the variations of the performance on different jobsets. The experimental results demonstrate that the deep reinforcement learning get improved scheduling efficiency in cluster computing. The performance advantage is more obvious when the load gets heavier.

关键词： Deep reinforcement learning Schedule Cluster Policy gradient Fusion baseline

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement learning-based Task Scheduling Algorithm for Energy Efficiency in Data Centers 30

A Deep Reinforcement Learning-based Task Scheduling Algorith...

引用

30th international conference on Computer Communications and Networks (ICCCN)

作者： Song, Penglei Chi, Ce Ji, Kaixuan Liu, Zhiyong Zhang, Fa Zhang, Shikui Qiu, Dehui Wan, Xiaohua Capital Normal Univ Informat Engn Coll Beijing Peoples R China Chinese Acad Sci High Performance Comp Res Ctr Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9780738113302

Cloud data centers provide end-users with a wide range of application scenarios, including scientific computing, smart grids, etc. The number and size of data centers have rapidly increased in recent years, which causes severe environmental problems and colossal power demand. Therefore, it is desirable to use a proper scheduling method to optimize resource usage and reduce energy consumption in a data center. However, it is rather difficult to design an effective and efficient task scheduling algorithm because of the dynamic and complex environment of data centers. This paper proposes a task scheduling algorithm, WSS, to optimize resource usage and reduce energy consumption based on a model-free deep reinforcement learning framework inspired by the Wolpertinger architecture. The proposed algorithm can handle the scheduling problem on a sizeable discrete action space, improve decision efficiency, and save the training convergence time. Meanwhile, the proposed algorithm based on soft Actor-Critic is designed to improve the stability and exploration capability of WSS. Experiments based on real-world traces prove that WSS can reduce energy consumption by nearly 25% compared with the Deep Q-network task scheduling algorithm. Moreover, WSS can provide a short time of training convergence without increasing the average waiting time of tasks and achieve stable performance.

关键词： Cloud computing energy efficiency task scheduling deep reinforcement learning wolpertinger architecture

来源：评论

学校读者我要写书评

暂无评论

A Study of Data-Path Bugs in PyTorch with a Focus on Memory Issues

A Study of Data-Path Bugs in PyTorch with a Focus on Memory ...

引用

IEEE international conference on Big Data

作者： Rubayet Rahman Rongon Chen Cao Xuechen Zhang Washington State University Vancouver Washington Pennsylvania State University Behrend Erie Pennsylvania

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

This paper presents a comprehensive and quantitative study of bugs related to Data Path in PyTorch with a focus on tensor management in memory. The bugs were reported from 2017 to 2024. Analyzing 3,089 closed issues, we identified 11 distinct bug types affecting the data storage, allocation, and loading, including memory bugs, indexing errors, and tensor contiguity violations. Our analysis reveals that data-path bugs have more occurrences than bugs related to computation in PyTorch in recent years. Among the memory bugs, non-contiguity bugs account for 30.2% of the total number of bugs and they have the most significant impact, leading to both crashes and silent correctness failures. One of the common solutions to addressing non-contiguity bugs is transforming from non-contiguous data to contiguous data in memory before machine-learning computation. To assess the impact of memory layout transformation, we conducted experiments involving tensor augmentation and non-contiguous tensor conversion. Our findings demonstrate that maintaining tensor contiguity throughout the augmentation process can improve performance by up to 49.6%, while the time required for non-contiguous tensor conversion varies significantly based on the number and order of dimensions. Our research provides valuable insights for developers and researchers working with PyTorch, helping them to identify and address potential bugs in data paths and tensor memory management.

关键词： Tensors High performance computing Computer bugs Memory management Loading Layout machine learning Resource management Kernel Indexing

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Representation learning: Target Regularization for Cross-Domain Sentiment Classification 1

引用

22nd international conference on Artificial Intelligence and soft computing, ICAISC 2023

作者： Perelkiewicz, Michal Poświata, Rafal Kierzkowski, Jakub National Information Processing Institute Al. Niepodleglości 188B Warsaw Poland

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

This article proposes an autoencoder-based domain invariant feature representation learning approach to domain adaptation and the cross-domain text classification problem. Finding domain invariant feature representations is a transfer learning method for transmitting knowledge between source and target domain data. Our method aims to avoid the overfitting of an autoencoder model on source domain training data in a trained embedded feature space using a target regularization technique. We hypothesize that when forcing the semantic similarity of target domain representation to source domain representation by adding the source domain similarity penalty to reconstruction loss during autoencoder training, the penalty is greater when the the domain’s representations separability is. In this work, we contribute to domain adaptation by demonstrating that a regularization technique based on an auxiliary pretrained domain classification model can be used to build robust, shared domain feature representations. Our model achieves a classification accuracy improvement in standard cross-domain sentiment classification tasks over the baseline model in most cases. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Data Balance Optimization of Fraud Classification for E-Commerce Transaction

Data Balance Optimization of Fraud Classification for E-Comm...

引用

international conference on Informatics and computing (ICIC)

作者： Aida Fitriyani Wowon Priatna Tyastuti Sri Lestari Dwipa Handayani TB Ai Munandar Amri Informatics Universitas Bhayangkara Jakarta Raya Jakarta Indonesia Digital Businesses Atma Luhur Saints and Business Institute Bangka Belitung Indonesia

ISBN: (纸本)9798350345728

The purpose of this study is to solve the problem of unbalanced data for prediction and classification of fraudulent E-Commerce transactions. Data from Digital Commerce 360 in 2015 showed that fraud occurred as much as 35% of total e-commerce transactions. Quoted from ***, based on the 2017 Fraud Management Insight report, this percentage of fraud can reduce consumer confidence. One method for predicting fraud is machine learning. Fraud data does not have a balance between data that is not fraudulent, causing the classification to be biased. So it is necessary to balance the data using the SMOTE algorithm. The results of the data balancing will be classified as fraudulent transactions using the Support vector machine, K-Nearst Neighbor, Naïve Bayes and C45 algorithms.

关键词： Support vector machines machine learning algorithms Support vector machine classification machine learning Prediction algorithms Fraud Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Single and Hybrid Neuro-Fuzzy-Based Models for an Industrial Heating Ventilation and Air Conditioning Control System

Comparative Analysis of Single and Hybrid Neuro-Fuzzy-Based ...

引用

RIVF international conference on computing and Communication Technologies (RIVF)

作者： Ardabili, Sina Beszedes, Bertalan Nadai, Laszlo Szell, Karoly Mosavi, Amir Imre, Felde Univ Pannonia Inst Adv Studies Koszeg Koszeg Hungary Obuda Univ Alba Regia Tech Fac Budapest Hungary Obuda Univ Kalman Kando Fac Elect Engn Budapest Hungary J Selye Univ Dept Math & Informat Komarno Slovakia Bauhaus Univ Weimar Weimar Germany

ISBN: (数字)9781728153773

ISBN: (纸本)9781728153773

Hybridization of machine learning methods with soft computing techniques is an essential approach to improve the performance of the prediction models. Hybrid machine learning models, particularly, have gained popularity in the advancement of the high-performance control systems. Higher accuracy and better performance for prediction models of exergy destruction and energy consumption used in the control circuit of heating, ventilation, and air conditioning (HVAC) systems can be highly economical in the industrial scale to save energy. This research proposes two hybrid models of adaptive neuro-fuzzy inference system-particle swarm optimization (ANFIS-PSO), and adaptive neuro-fuzzy inference system-genetic algorithm (ANFIS-GA) for HVAC. The results are further compared with the single ANFIS model. The ANFIS-PSO model with the RMSE of 0.0065, MAE of 0.0028, and R-2 equal to 0.9999, with a minimum deviation of 0.0691 (KJ/s), outperforms the ANFIS-GA and single ANFIS models.

关键词： Adaptive neuro-fuzzy inference system ANFIS-PSO ANFIS-GA HVAC hybrid machine learning

来源：评论

学校读者我要写书评

暂无评论

Pruning Convolutional Filters via Reinforcement learning with Entropy Minimization 1

引用

22nd international conference on Artificial Intelligence and soft computing, ICAISC 2023

作者： Muşat, Bogdan Andonie, Răzvan Department of Electrical Engineering and Computer Science Transilvania University of BraŞov BraŞov Romania Department of Computer Science Central Washington University Ellensburg United States

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

Structural pruning has become an integral part of neural network optimization, used to achieve architectural configurations which can be deployed and run more efficiently on embedded devices. Previous results showed that pruning is possible with minimum performance loss by utilizing a reinforcement learning agent which makes decisions about the sparsity level of each neural layer by maximizing as a reward the accuracy of the network. We introduce a novel information-theoretic reward function which minimizes the spatial entropy of convolutional activations. This minimization ultimately acts as a proxy for maintaining accuracy, although these two criteria are not related in any way. Our method shows that there is another possibility to preserve accuracy without the need to directly optimize it in the agent’s reward function. In our experiments, we were able to reduce the total number of FLOPS of multiple popular neural network architectures by 5–10 ×, incurring minimal or no performance drop and being on par with the solution found by maximizing the accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Computational methods to retrieve soil moisture using remote sensing data: A review

Computational methods to retrieve soil moisture using remote...

引用

international conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Raja Inoubli Daniel Enrique Constantino-Recillas Alejandro Monsiváis-Huertero Lilia Bennaceur Farah Imed Riadh Farah National School of Computer Science Labratoire RIADI Manouba Tunisia Tecnolóogico Nacional de Méexico / TES de Ecatepec Mexico City Mexico ESIME Ticomáan Instituto Politéecnico Nacional Mexico City Mexico LTSIRS laboratory Preparatory Institute for Engineering Studies El Manar and National Institute of Engineering Sciences of Tunis Manar Tunisia

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

Recently, soil moisture (SM) retrieval has become the first interest of the scientific community due to the increasing demand for water resources in several fields, especially the agricultural sector. A lack of such resources has been detected along with the increasing climate changes and disasters occurring such as drought. It has become very essential to search for efficient approaches and data sources that can serve effectively the SM retrieval goals. This paper is a literature review set to identify the strengths and weaknesses of the most relevant works in the area of SM retrieval and Remote Sensing (RS) published from 2017 to 2024. Summarizing the selected studies serves to detect the relevant information that tackles the SM retrieval challenges. Thus, creating new horizons for new research. One of the main fields of interest is SM retrieval over agriculture based on the synergistic use of Sentinel-1 (S-1) and Sentinel-2 (S-2) images. High accuracy has been achieved by combining different approaches such as backscattering models and machine learning (ML) algorithms (e.g., AIEM and NN algorithms). The application of such a combination is highly recommended due to its promising potential.

关键词： Accuracy machine learning algorithms Bibliographies soft sensors Soil moisture Estimation Sentinel-1

来源：评论

学校读者我要写书评

暂无评论

Risk Prediction of P2P Credit Loans Overdue Based on Gradient Boosting machine Model

Risk Prediction of P2P Credit Loans Overdue Based on Gradien...

引用

2021 IEEE international conference on Power, Intelligent computing and Systems, ICPICS 2021

作者： Zhu, Xueping Chen, Jichang Nanning University School of Information Engineering Nanning China

ISBN: (纸本)9781665441308

With the gradual integration of online lending into our lives, the credit risk issues it brings have also attracted attention. Credit risk issues not only make the lending platform significantly increase financing costs but also affect the average yield of lending users. Therefore, we collected truthful user data from a P2P company, which counted 3,000 P2P user information while including 446 feature elements, which also conducted a lending user overdue risk prediction study on the collected data. The research content is mainly to explore and clean the data, dig out the significant factors affecting the users' repayment overdue, modeling the late repayment rate of P2P credit users by data analysis method, and finally ROC curve to evaluate the model performance. The research provides more objective and comprehensive analysis and prediction of the late repayment rate of credit users in the data. The experimental results show that the GBM model can be applied to credit late repayment prediction and avoid the limitations of some models. According to the above mining results, P2P enterprises can be more reasonable and efficient to carry out risk management, identify high-risk credit loans. So that enterprises can be more sustainable and steady development. © 2021 IEEE.

关键词： machine learning

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275页 << < 30 31 32 33 34 35 36 37 38 39 > >>

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：