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

628 篇 会议
3 册 图书
2 篇 期刊文献

馆藏范围

633 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

532 篇 工学
- 486 篇 计算机科学与技术...
- 252 篇 软件工程
- 96 篇 信息与通信工程
- 78 篇 生物工程
- 40 篇 生物医学工程（可授...
- 36 篇 电气工程
- 19 篇 控制科学与工程
- 15 篇 光学工程
- 12 篇 动力工程及工程热...
- 11 篇 交通运输工程
- 9 篇 建筑学
- 9 篇 安全科学与工程
- 8 篇 仪器科学与技术
- 8 篇 化学工程与技术
181 篇 理学
- 83 篇 生物学
- 80 篇 数学
- 47 篇 物理学
- 36 篇 系统科学
- 33 篇 统计学（可授理学、...
- 10 篇 化学
76 篇 医学
- 69 篇 临床医学
- 29 篇 基础医学(可授医学...
- 22 篇 药学(可授医学、理...
- 16 篇 公共卫生与预防医...
70 篇 管理学
- 40 篇 图书情报与档案管...
- 34 篇 管理科学与工程(可...
- 23 篇 工商管理
27 篇 教育学
- 25 篇 教育学
21 篇 法学
- 19 篇 社会学
10 篇 文学
- 8 篇 外国语言文学
5 篇 经济学
4 篇 农学
1 篇 军事学
1 篇 艺术学

主题

157 篇 machine learning
78 篇 deep learning
26 篇 reinforcement le...
16 篇 neural networks
16 篇 machine learning...
15 篇 covid-19
14 篇 support vector m...
13 篇 transfer learnin...
12 篇 artificial intel...
10 篇 learning systems
9 篇 internet of thin...
9 篇 mobile learning
9 篇 classification
9 篇 training
9 篇 convolutional ne...
8 篇 object detection
8 篇 gamification
8 篇 image processing
8 篇 federated learni...
7 篇 natural language...

机构

5 篇 de la salle univ...
4 篇 tokai univ sch i...
4 篇 chuo univ fac sc...
3 篇 university of sc...
3 篇 infn sezione di ...
3 篇 centre for space...
3 篇 infn sezione di ...
3 篇 grupo de electro...
3 篇 univ western mac...
3 篇 national astrono...
3 篇 infn dipartiment...
3 篇 pontificia unive...
3 篇 univ johannesbur...
3 篇 eth zurich insti...
3 篇 institute for co...
3 篇 the barcelona in...
3 篇 universidad naci...
3 篇 hechi univ dept ...
3 篇 centre for advan...
3 篇 university of na...

作者

4 篇 aloisio r.
4 篇 namatame takashi
4 篇 otake kohei
3 篇 berti a.
3 篇 arcaro c.
3 篇 abe h.
3 篇 bastieri d.
3 篇 böttcher m.
3 篇 ambrosi g.
3 篇 bamba a.
3 篇 bonanno g.
3 篇 arqueros f.
3 篇 amati l.
3 篇 barrio j.a.
3 篇 bellizzi l.
3 篇 ambrosio m.
3 篇 arbet-engels a.
3 篇 novais paulo
3 篇 ambrogi l.
3 篇 babic a.

语言

630 篇 英文
3 篇 其他

检索条件"任意字段=2021 13th International Conference on Machine Learning and Computing, ICMLC 2021"

共 633 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：

2021 13th international conference on machine learning and computing, icmlc 2021

2021 13th International Conference on Machine Learning and C...

引用

2021 13th international conference on machine learning and computing, icmlc 2021

ISBN: (纸本)9781450389310

the proceedings contain 91 papers. the topics discussed include: applications of machine learning techniques in genetic circuit design;efficient domain-specific news push service using deep learning based text regression without usersâ€™ information;online optimal investment portfolio model based on deep reinforcement learning;research on flow classification model based on similarity and machine learning algorithm;factors affecting accuracy of genotype imputation using neural networks in deep learning;algorithmic generation of positive samples for compound-target interaction prediction;using deep learning to construct auto web penetration test;acoustic classification of bird species using wavelets and learning algorithms;and an enhanced adaptive large neighborhood search algorithm for the capacitated vehicle routing problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

machine learning Methods and Models, Predictive Analytics and Applications - Proceedings of the Workshop on the 13th international Scientific Practical conference Modern Problems of Social and Economic Systems Modelling, MPSESM-W 2021

Machine Learning Methods and Models, Predictive Analytics an...

引用

machine learning Methods and Models, Predictive Analytics and Applications - 13th Workshop on the international Scientific Practical conference Modern Problems of Social and Economic Systems Modelling, MPSESM-W 2021

the proceedings contain 11 papers. the topics discussed include: machine learning methods and models, predictive analytics and applications: development trends in the post-crisis syndrome caused by COVID-19;COVID-19 measures sentiment analysis based on a social network dataset;risk assessment of innovative projects: development of forecasting models;models for forecasting innovative development of the economy of resort-recreational sphere;methods and models of machine learning in managing the market value of the company;set of models for assessing knowledge in distance learning systems;derivative pricing: predictive analytics methods and models;applying of data envelopment analysis to study public administration effectiveness during a pandemic;determinants of social trust: analysis using machine learning methods;and clustering approach to analysis of the credit risk and profitability for nonbank lenders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discovering Optimal Subspaces in Deep Architectures for Offline Signature Verification 24

Discovering Optimal Subspaces in Deep Architectures for Offl...

引用

13th international conference on computing and Pattern Recognition, ICCPR 2024

作者： Zhu, Qifeng Zhang, Benzhuang Yuan, Limengzi Ren, Yuanyuan Zhao, Qingzhan Zheng, Yuchen College of Information Science and Technology Shihezi University Shihezi China Dalian University of Technology Dalian China

ISBN: (纸本)9798400717482

In offline signature verification systems, deep learning-based feature extractors often fix the feature space for feature extraction, which may not obtain the best features for subsequent verification tasks. To address this issue, this paper proposes a novel framework that controls the dimensionality of features by stretching and reducing deep features to obtain the best features. Specifically, deep features can be stretched through a higher-dimensional projection matrix whose elements are randomly sampled from a standard normal distribution to obtain a more discriminative representation, and further reduced by Linear Discriminant Analysis (LDA) to more effectively capture the subtle differences between different signers. In this way, the learned features can be scaled to any optimal subspace. Extensive experimental results and discussions show that the proposed method improves the performance of deep learning-based offline signature verification systems and surpasses existing state-of-the-art verification systems on three benchmark datasets. © 2024 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

4th international Workshop on machine learning for Medical Image Reconstruction, MLMIR 2021 held in Conjunction with 24th international conference on Medical Image computing and Computer Assisted Intervention, MICCAI 2021

4th International Workshop on Machine Learning for Medical I...

引用

4th international Workshop on machine learning for Medical Image Reconstruction, MLMIR 2021 held in Conjunction with 24th international conference on Medical Image computing and Computer Assisted Intervention, MICCAI 2021

ISBN: (纸本)9783030885519

the proceedings contain 13 papers. the special focus in this conference is on machine learning for Medical Image Reconstruction. the topics include: Real-Time Video Denoising to Reduce Ionizing Radiation Exposure in Fluoroscopic Imaging;a Frequency Domain Constraint for Synthetic and Real X-ray Image Super Resolution;semi- and Self-supervised Multi-view Fusion of 3D Microscopy Images Using Generative Adversarial Networks;efficient Image Registration Network for Non-Rigid Cardiac Motion Estimation;Evaluation of the Robustness of Learned MR Image Reconstruction to Systematic Deviations Between Training and Test Data for the Models from the fastMRI Challenge;Self-supervised Dynamic MRI Reconstruction;A Simulation Pipeline to Generate Realistic Breast Images for learning DCE-MRI Reconstruction;Deep MRI Reconstruction with Generative Vision Transformers;Distortion Removal and Deblurring of Single-Shot DWI MRI Scans;One Network to Solve them All: A Sequential Multi-task Joint learning Network Framework for MR Imaging Pipeline;Physics-Informed Self-supervised Deep learning Reconstruction for Accelerated First-Pass Perfusion Cardiac MRI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WConF: Weighted Contrastive Fusion for Multimodal Sentiment Analysis 13th

WConF: Weighted Contrastive Fusion for Multimodal Sentiment ...

引用

13th international conference on Natural Language Processing and Chinese computing

作者： Zeng, Biqing Li, Ruiyuan Lu, Liuxing Lu, Liangqi Wang, Jiazhen Chen, Weihai Dong, Huimin South China Normal Univ Sch Software Foshan Peoples R China South China Normal Univ Aberdeen Inst Data Sci & Artificial Intelligence Foshan Peoples R China South China Normal Univ Sch Econ & Management Guangzhou Peoples R China Guangdong AIB Polytech Sch Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9789819794423;9789819794430

With the continuous development of multimedia, Multimodal Sentiment Analysis has become a highly regarded field. Recent research proposes learning effective unimodal representations to facilitate multimodal fusion, which mainly contain two parts of information: modality-common and modality-specific information. However, previous work does not consider the sentiment span information between different samples during the fusion process. In this paper, we propose a novel framework Weighted Contrastive Fusion (WConF) to extract sentiment span information for multimodal fusion. First, we apply modality contrastive learning to capture modality-common sentiment information and separate modality-specific sentiment information. then, considering sentiment spans as weights, we perform weighted contrastive learning on the multimodal representations. Moreover, we design a loss function to assist in weighted contrastive fusion. Finally, we conduct extensive experiments on four benchmark datasets: MOSI, MOSEI, CH-SIMS, and CH-SIMSV2. Experimental results demonstrate that our model achieves superior performance compared to previous models.

关键词： Weighted Contrastive Fusion Multimodal Sentiment Analysis Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

13th international conference on Interactive Mobile Communication, Technologies and learning, IMCL 2019

13th International Conference on Interactive Mobile Communic...

引用

13th international conference on Interactive Mobile Communication, Technologies and learning, IMCL 2019

ISBN: (纸本)9783030499310

the proceedings contain 105 papers. the special focus in this conference is on Interactive Mobile Communication, Technologies and learning. the topics include: A Fiber Wireless A-RoF/IFoF Uplink Transmission of up to 0.6 Gb/s User Data Rate Over a 32-Element 60 GHz Beam-Steering Antenna for 5G Fronthaul Networks;an eHealth-Care Driven Perspective on 5G Networks and Infrastructure;25 Gb/s Colorless Transmitter Based on Reflective Electroabsorption Modulator for Ultra-Dense WDM-PON Application;Challenges of Using Phased Array Antennas in Commercial Backhaul Equipment at 26 GHz;towards Intelligent Multi-Access Edge computing Using machine learning;Performance Analysis of NB-IoT Random Access Channel;work-in-Progress: Development of a Framework for Incorporating Usability Aspects with Digital Didactical Design for Mobile/Tablet Based learning in Pre-primary Education;Promoting Authentic Student Assessment for STEM Project-Based learning Activities;predictive Modeling Concerning Mobile learning Advance;assessing Early Grade Mathematics Learner Outcomes Using m-learning: the Case of JumpStart South Africa;Users’ and Experts’ Evaluation of TARGET: A Serious Game for Mitigating Performance Enhancement Culture in Youth;poster: Exploring the Educational Affordances of an Academic ePortfolio for Engineer Students through a Self-regulated learning Framework;m-Health as a Tool in the Cognitive Flexibility of the Elderly;Critical Categorization of Android and IOS Applications Available for STEAM Education in Early Childhood;museum Exhibits that Interact with Pupils’ Mobile Devices. the Case of Hellenic Maritime Museum;linkLearn: Blockchain Technology as a learning Tool;can Elementary Students Co-design the learning Content of Educational Apps: the We!Design!Fractions Participatory Design Approach;pedagogical Considerations for Mobile-Based Augmented Reality learning Environments;dynamic Mobile Student Response System.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Feasible Deep learning Approach Using EEG for Neurodegenerative Diseases 13

Towards Feasible Deep Learning Approach Using EEG for Neurod...

引用

13th international Winter conference on Brain-Computer Interface, BCI 2025

作者： Park, Dogeun Kim, Ho-Jung Ju, Young-Gi Kim, Keun-Tae Won, Dong-Ok Dept. Artificial Intelligence Convergence Hallym University Chuncheon Korea Republic of Dept. Artificial Intelligence Convergence College of Medicine Hallym University Chuncheon Korea Republic of

ISBN: (纸本)9798331521929

In this study, we propose the phase space reconstruction (PSR)-based deep learning framework for enhanced detection of frontotemporal dementia (FTD) utilizing electroencephalography (EEG). Our experimental results demonstrate significant improvements over conventional screening methods, particularly the mini-mental state examination (MMSE), which exhibits a considerable false-negative rate of 39.1% in FTD screening. the proposed framework achieved a remarkable 88.89% accuracy in identifying previously misclassified FTD cases. the evaluation was conducted using a public dataset comprising 23 FTD patients and 29 healthy controls, wherein our framework consistently outperformed both traditional MMSE and the EEGNet-based approach. through the integration of PSR techniques with advanced deep learning architectures, our findings suggest that EEG-based computational approaches could serve as robust complementary diagnostic tools in clinical FTD assessment protocols. these results underscore the potential of machine learning applications in enhancing the accuracy and reliability of neurological disorder diagnosis. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Modeling Comparative Logical Relation with Contrastive learning for Text Generation 13th

Modeling Comparative Logical Relation with Contrastive Learn...

引用

13th international conference on Natural Language Processing and Chinese computing

作者： Dan, Yuhao Tian, Junfeng Zhou, Jie Yan, Ming Zhang, Ji Chen, Qin He, Liang East China Normal Univ Lab Artificial Intelligence Educ Shanghai Peoples R China ECNU Shanghai Inst Artificial Intelligence Educ Shanghai Peoples R China ECNU Sch Comp Sci & Tecluiol Shanghai Peoples R China Xiaohongshu Inc Shanghai Peoples R China Alibaba Grp Hangzhou Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Data-to-Text Generation (D2T), a classic natural language generation problem, aims at producing fluent descriptions for structured input data, such as a table. Existing D2T works mainly focus on describing the superficial associative relations among entities, while ignoring the deep comparative logical relations, such as A is better than B in a certain aspect with a corresponding opinion, which is quite common in our daily life. In this paper, we introduce a new D2T task named comparative logical relation generation (CLRG). Additionally, we propose a Comparative Logic (CoLo) based text generation method, which generates texts following specific comparative logical relations with contrastive learning. Specifically, we first construct various positive and negative samples by fine-grained perturbations in entities, aspects and opinions. then, we perform contrastive learning in the encoder layer to have a better understanding of the comparative logical relations, and integrate it in the decoder layer to guide the model to correctly generate the relations. Noting the data scarcity problem, we construct a Chinese Comparative Logical Relation Dataset (CLRD), which is a high-quality human-annotated dataset and challenging for text generation with descriptions of multiple entities and annotations on their comparative logical relations. Extensive experiments show that our method achieves impressive performance in both automatic and human evaluations.

关键词： Natural language processing Data-to-text generation Contrastive learning Dataset construction

来源：评论

学校读者我要写书评

暂无评论

GSEA: Global Structure-Aware Graph Neural Networks for Entity Alignment 13th

GSEA: Global Structure-Aware Graph Neural Networks for Entit...

引用

13th international conference on Natural Language Processing and Chinese computing

作者： Wang, Cunda Wang, Weihua Liang, Qiuyu Yu, Jie Gao, Guanglai Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China Natl & Local Joint Engn Res Ctr Intelligent Infor Hohhot Peoples R China Inner Mongolia Key Lab Multilingual Artificial In Hohhot Peoples R China Natl Univ Def Technol Coll Comp Sci Changsha Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Entity alignment (EA) aims to identify the same real-world entities presented in different knowledge graphs (KGs), which is the most crucial step in integrating multi-source KGs. Existing entity alignment methods based on Graph Neural Networks mainly focus on aggregating neighborhood structure information within the original graph to generate entity embeddings. However, these methods fail to effectively leverage the global structural information of entities. In this paper, we propose a novel method based on Global Structure-Aware Graph Neural Networks to capture the global structure between entities. Specifically, our method learns global embeddings from the augmented graph reconstructed by Singular Value Decomposition. Moreover, we employ contrastive learning to maximize the consistency between global and local embeddings while mitigating the over-smoothing problem. Extensive experimental results on benchmark datasets, along with further analysis, demonstrate the superiority and effectiveness of our method. the source code is available at https://***/wonderCS1213/GSEA.

关键词： Knowledge graph Entity alignment Graph neural networks Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

TARGET: Template-Transferable Backdoor Attack Against Prompt-Based NLP Models via GPT4 13th

TARGET: Template-Transferable Backdoor Attack Against Prompt...

引用

13th international conference on Natural Language Processing and Chinese computing

作者： Tan, Zihao Chen, Qingliang Huang, Yongjian Liang, Chen Jinan Univ Dept Comp Sci Guangzhou 510632 Peoples R China Guangzhou Xuanyuan Res Inst Co Ltd Guangzhou 510006 Peoples R China Hong Kong Polytech Univ Dept Comp Hung Hom Kowloon Hong Kong Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Prompt-based learning has been widely applied in many low-resource natural language processing (NLP) tasks such as few-shot scenarios. However, this paradigm has been shown to be vulnerable to backdoor attacks. Most of the existing attack methods focus on inserting manually predefined templates as triggers in the pre-training phase to train the victim model and utilize the same triggers in the downstream task to perform inference, which tends to ignore the transferability and stealthiness of the templates. In this work, we propose a novel approach of TARGET, which is a data-independent attack method. Specifically, we first utilize GPT4 to reformulate manual templates to generate tone-strong and normal templates, and the former are injected into the model as a backdoor trigger in the pre-training phase. then, we not only directly employ the above templates in the downstream task, but also use GPT4 to generate templates with similar tone to the above templates to carry out transferable attacks. Finally we have conducted extensive experiments on five NLP datasets and three BERT series models, with experimental results justifying that our TARGET method has better attack performance and stealthiness compared to the two-external baseline methods on direct attacks, and in addition achieves satisfactory attack capability in the unseen tone-similar templates.

关键词： Prompt-based learning Backdoor Attack Few-shot Classification Tasks

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64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：