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

214 篇 会议
81 篇 期刊文献
3 册 图书

馆藏范围

298 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

168 篇 工学
- 137 篇 计算机科学与技术...
- 112 篇 软件工程
- 35 篇 生物工程
- 31 篇 生物医学工程（可授...
- 24 篇 信息与通信工程
- 24 篇 控制科学与工程
- 21 篇 光学工程
- 18 篇 电气工程
- 16 篇 电子科学与技术（可...
- 8 篇 化学工程与技术
- 7 篇 土木工程
- 7 篇 安全科学与工程
- 6 篇 仪器科学与技术
111 篇 理学
- 56 篇 数学
- 36 篇 生物学
- 33 篇 物理学
- 28 篇 统计学（可授理学、...
- 12 篇 系统科学
- 11 篇 化学
- 7 篇 地球物理学
35 篇 管理学
- 18 篇 图书情报与档案管...
- 17 篇 管理科学与工程(可...
- 9 篇 工商管理
22 篇 医学
- 20 篇 临床医学
- 19 篇 基础医学(可授医学...
- 14 篇 药学(可授医学、理...
- 6 篇 公共卫生与预防医...
8 篇 农学
- 8 篇 作物学
6 篇 法学
- 6 篇 社会学
5 篇 教育学
- 5 篇 教育学
4 篇 经济学
1 篇 文学

主题

22 篇 accuracy
14 篇 training
12 篇 machine learning
11 篇 deep learning
10 篇 feature extracti...
8 篇 support vector m...
8 篇 artificial intel...
7 篇 predictive model...
7 篇 real-time system...
7 篇 machine learning...
7 篇 convolutional ne...
6 篇 computational mo...
6 篇 computer vision
5 篇 reliability
5 篇 medical services
5 篇 optimization
5 篇 prediction algor...
4 篇 internet of thin...
4 篇 sensitivity
4 篇 adversarial mach...

机构

5 篇 centre for cogni...
4 篇 ai and machine l...
4 篇 lovely professio...
4 篇 data61 commonwea...
4 篇 australian insti...
4 篇 data science and...
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 compute...
3 篇 dept. of electri...
3 篇 darmstadt
3 篇 dept. of physics...
3 篇 uit machine lear...
3 篇 machine learning...
3 篇 dept. of compute...
3 篇 dept. of electri...
3 篇 dept. of languag...

作者

6 篇 shams mahmoud y.
5 篇 horváth tamás
5 篇 wrobel stefan
5 篇 kersting kristia...
5 篇 gordon geoffrey ...
4 篇 hong xudong
4 篇 demberg vera
4 篇 bianchi filippo ...
4 篇 mahmoud y. shams
4 篇 müller klaus-rob...
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...
3 篇 jenssen robert
3 篇 sharmila l.
3 篇 kettimuthu rajku...

语言

284 篇 英文
14 篇 其他

检索条件"机构=Dept. of Machine Learning and Data Science"

共 298 条记录，以下是11-20 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：

Stochastic Large-scale machine learning Algorithms with Distributed Features and Observations

Stochastic Large-scale Machine Learning Algorithms with Dist...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Fang, Biyi Klabjan, Diego Vo, Truong Northwestern University Dept. of Engineering and Applied Mathematics EvanstonIL60208 United States Northwestern University Dept. of Industrial Engineering and Management Sciences EvanstonIL60208 United States Northwestern University Dept. of Machine Learning and Data Science EvanstonIL60208 United States

ISBN: (纸本)9798350362480

As the size of modern datasets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing. Given that optimization is one of the pillars of machine learning and predictive modeling, distributed optimization methods have recently garnered ample attention, in particular when either observations or features are distributed, but not both. We propose a general stochastic algorithm where observations, features, and gradient components can be sampled in a double distributed setting, i.e., with both features and observations distributed. Very technical analyses establish convergence properties of the algorithm under different conditions on the learning rate (diminishing to zero or constant). Computational experiments in Spark demonstrate a superior performance of our algorithm versus a benchmark in early iterations of the algorithm, which is due to the stochastic components of the algorithm. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

PAC-Bayes-Chernoff bounds for unbounded losses 38

PAC-Bayes-Chernoff bounds for unbounded losses

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Casado, Ioar Ortega, Luis A. Pérez, Aritz Masegosa, Andrés R. Spain Machine Learning Group Computer Science Dept. EPS Universidad Autónoma de Madrid Spain Department of Computer Science Aalborg University Denmark

We introduce a new PAC-Bayes oracle bound for unbounded losses that extends Cramér-Chernoff bounds to the PAC-Bayesian setting. The proof technique relies on controlling the tails of certain random variables involving the Cramér transform of the loss. Our approach naturally leverages properties of Cramér-Chernoff bounds, such as exact optimization of the free parameter in many PAC-Bayes bounds. We highlight several applications of the main theorem. Firstly, we show that our bound recovers and generalizes previous results. Additionally, our approach allows working with richer assumptions that result in more informative and potentially tighter bounds. In this direction, we provide a general bound under a new model-dependent assumption from which we obtain bounds based on parameter norms and log-Sobolev inequalities. Notably, many of these bounds can be minimized to obtain distributions beyond the Gibbs posterior and provide novel theoretical coverage to existing regularization techniques. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Customer Behaviour Analysis: Tools Overview 2

Customer Behaviour Analysis: Tools Overview

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Bharti, Jigyasa Dongre, Snehlata Thorat, Mayuri G H Raisoni College of Engineering Dept. of Computer Science and Engineering Nagpur India PES's Modern College of Engineering Dept. of Artificial Intelligence and Machine Learning Pune India

ISBN: (纸本)9798350383287

Analytics is a process of collecting and analyzing data that can help in taking meaningful decisions. The data is collected from various sources, this raw data is then processed and converted to dashboards which assists in business analyzation. Analytics are of various types such as descriptive, diagnostic, predictive, prescriptive and text. One area of analytics is Business Intelligence which is a broader concept of using various tools and methods that involves presentation of business data to support decision making. Customer behavioral analysis can be conducted by having insights from web analytics. It is a process of understanding how a customer is responding to a website. Regular improvements can be done to increase customer interaction, enhance user experience and data-driven decision-making. In this paper, we will be discussing two major tools that are used for behavior analysis. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Dermatology: Revolutionizing Dermatological Diagnostics with AI and Emergency Care Solutions 3

Next-Gen Dermatology: Revolutionizing Dermatological Diagnos...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Yashas, D. Kashyap, M. Shivani Charan, P.R. Hemanth Kumar, G.P. Abhishek, B.K. Deekshith, C. New Horizon College of Engineering Dept of Artificial Intelligence and Machine Learning Bengaluru India New Horizon College of Engineering Dept of Information Science and Engineering Bengaluru India Bnm Institute of Technology Dept of Artificial Intelligence and Machine Learning Bengaluru India Siddaganga Institute of Technology Dept of Artificial Intelligence and Data Science Tumkur India Vidyavardhaka College of Engineering Dept of Computer Science and Engineering Mysore India

ISBN: (纸本)9798331515911

Skin health conditions should be diagnosed and treated on time so as to prevent complications and promote better health results. This paper presents an AI-based system that makes use of Convolutional Neural Networks with the InceptionV3 Architecture for predicting skin diseases at higher levels. The model, which is based on the large DermaNet dataset, classifies skin disorders fast and effectively. The system is coupled with a simple Telegram based application for the users to get a complete solution. A user can upload a photo of the affected skin area and get a diagnosis within seconds, an explanation of the disease and how severe it is in percentage. The bot also has a location and contact sharing feature that assists users in finding nearby doctors and clinics that can provide further assistance. It further provides on the spot appropriate cures for the particular condition diagnosed. Moreover, this makes it possible for the customer to fill the healthcare void in particular the neglected ones by making it easy for them to access real time high quality services. By equipping users with relevant information and appropriate actions required at the right time, this project has showcased how AI has the ability to transform the dermatological field. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy Efficiency and Network Performance in Smart Street Lighting Systems Using LoRaWAN Technology 3

Optimizing Energy Efficiency and Network Performance in Smar...

引用

3rd IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing, INCOS 2024

作者： Sivakumar, S. Jayanth, R. Mughesh Kumar, N.R. Srm Institute of Science and Technology Dept. of Comp. Sci. and Engineering Specialization in Artificial Intelligence and Machine Learning Tamil Nadu Tiruchirapalli India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361186

This paper presents a groundbreaking Smart Street Lighting System utilizing LoRaWAN technology to overcome the challenges of scalability, energy inefficiency, and communication limitations inherent in older smart street technologies. The system employs seamless, long-range communication for real-time monitoring, adapting to dynamic urban environments, and achieving a balance between energy conservation and public safety. Advanced components, including a Passive Infrared (PIR) sensor and microwave motion sensor, enhance object detection and urban safety. A unique feature of the system is its ability to automatically dim the street lights to 1/4th intensity when no object is detected, while instantly adjusting to full brightness upon object detection. Furthermore, the incorporation of a response factor ensures accurate detection and swift response to communication disruptions. Notably, the system achieves an outstanding 70% energy savings through optimized lighting and dynamic remote control, significantly contributing to the evolution of intelligent and energy-efficient street lighting solutions in smart city infrastructures. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Enhanced Vision Transformer with Lion Optimizer for Accurate Classification of Monkeypox Skin Images 4

Enhanced Vision Transformer with Lion Optimizer for Accurate...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Bhatnagar, Roheet Hassan, Esraa Saber, Abeer Shams, Mahmoud Y. Elbedwehy, Samar Manipal University Jaipur Department of Computer Science and Engineering Rajasthan India Kafrelsheikh University Faculty of Artificial Intelligence Dept. of Machine Learning Kafrelsheikh33516 Egypt Damietta University Faculty of Computers and Artificial Intelligence Information Technology Dept. Damietta34517 Egypt Kafrelsheikh University Faculty of Artificial Intelligence Dept. of Data Science Kafrelsheikh33511 Egypt

ISBN: (纸本)9798350387490

Monkeypox is a contagious viral infection caused by the monkeypox virus (Mpoxvirus). Characterized by skin lesions, fever, respiratory difficulties, swollen lymph nodes, and neurological complications, MPX can be fatal. Recent outbreaks have spread the disease across Europe, Australia, the United States, and Africa. Traditionally diagnosed through PCR testing of skin lesions, this process poses significant risks to medical personnel due to potential exposure to the highly contagious virus. However, the usage artificial intelligence (AI) is revolutionizing diagnostics, providing a safer and more efficient approach to MPX detection. In this paper, a new AI technique based on vision transformer and lion optimizer for classifying Monkeypox Skin Images. The presented model used for classifying the dataset and results reached accuracy of 99.6%. © 2024 IEEE.

关键词： Classification Deep learning Diagnosis Monkeypox

来源：评论

学校读者我要写书评

暂无评论

Edge Computing Devices Authentication using Quantum Computing 15

Edge Computing Devices Authentication using Quantum Computin...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Telsang, Vinayak A. Kakkasageri, Mahabaleshwar S. Devangavi, Anil D. Dept. of Computer Science and Engineering Biluru Gurubasava Mahaswamiji Institute of Technology Mudhol India Dept. Electronics and Communication Engineering Basaveshwar Engineering College Bagalkote India Dept. of Artificial Intelligence and Machine Learning Basaveshwar Engineering College Bagalkote India

ISBN: (纸本)9798350370249

Edge computing allows different technologies such as Internet of Things (IoT), vehicle-to-vehicle communications(VV), Industrial IOT (IIOT) to connect to the cloud computing to facilitate end users. The edge networks uses low bandwidth, and enhances the processing speed. With more number of IoT devices connected in the network the privacy of data stored at the edge server also under threat. Authentication is a major challenge which is be addressed to provide security and privacy to IoT devices connected in the network. The existing works uses cryptographic algorithms to solve the authentication problems, but with increase in growth of quantum computers and quantum computing, breaking the complex cryptographic algorithm is not an issue. Hence one should adopt the quantum approach to provide authentication in edge network. The proposed work uses quantum key and context information of IoT devices to store in the edge server using blockchain, which proves to be more secure. The performance analysis shows that it is better with respect to registration, encryption, decryption and authentication of IoT devices. ©2024 IEEE.

关键词： Authentication Blockchain Cryptography Edge computing Quantum key

来源：评论

学校读者我要写书评

暂无评论

Visual Coherence Loss for Coherent and Visually Grounded Story Generation 8

Visual Coherence Loss for Coherent and Visually Grounded Sto...

引用

8th Workshop on Representation learning for NLP, RepL4NLP 2023, co-located with ACL 2023

作者： Hong, Xudong Demberg, Vera Sayeed, Asad Zheng, Qiankun Schiele, Bernt Dept. of Computer Vision and Machine Learning MPI Informatics Germany Dept. of Language Science and Technology Dept. of Computer Science Saarland University Germany Dept. of Philosophy Linguistics and Theory of Science University of Gothenburg Sweden Saarland Informatics Campus Saarbrücken Germany

ISBN: (纸本)9781959429777

Local coherence is essential for text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story;(2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for learning image sequence representations. We further propose combining features from an object detector and a face detector to construct stronger character features. To evaluate visual grounding that current reference-based metrics do not measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories. Our code is available at https://***/vwprompt/vcl. © 2023 Association for Computational Linguistics.

关键词： Electric grounding

来源：评论

学校读者我要写书评

暂无评论

A Dual-Port, and Single-Element Planar Inverted-F Antenna for Current 4G/5G Portable Applications 21

A Dual-Port, and Single-Element Planar Inverted-F Antenna fo...

引用

21st International Multi-Conference on Systems, Signals and Devices, SSD 2024

作者： Alja'Afreh, Saqer S. Altakhaineh, Amjaad T. Al-Shamaileh, Mallak H. Matarneh, Aser M Daoud, Omar R. Al-Khawaldah I, Mohammad School of Engineering and Computing American International University Electrical and Computing Engineering Al-Jahra Kuwait Pioneers International Academy Data Science and Machine Learning Dept. Amman Jordan Al-Ahliyya Amman University Communications and Computer Engineering Amman Jordan

ISBN: (纸本)9798350374131

A first-hand, low-profile, two-port planar inverted-F antenna is proposed for current 4G/5G sub-3 GHz hand-portable multiple-input and multiple-output (MIMO) applications. The design features a profile of about 5 mm and dual-coplanar feeds, which are isolated using only a modified top plate, while the shared ground plane is not perturbed as in previous designs. An open-edge slot on the top of the PIFA provides a 3λ/4 current path. The proposed antenna covers approximately a 15% impedance bandwidth fraction in the range of 2.45-2.85 GHz. The simulated results, including scattering parameters, far-field radiation patterns, and the envelope correlation coefficient, all exhibit excellent features. © 2024 IEEE.

关键词： Antenna feeders

来源：评论

学校读者我要写书评

暂无评论

Decision-focused evaluation of worst-case distribution shift 24

Decision-focused evaluation of worst-case distribution shift

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Kevin Ren Yewon Byun Bryan Wilder Statistics and Data Science Dept. Carnegie Mellon University Pittsburgh Pennsylvania Machine Learning Dept. Carnegie Mellon University Pittsburgh Pennsylvania

Recent studies have shown that performance on downstream optimization tasks often diverges from standard accuracy-based losses, highlighting that the loss function of a predictive model should align with the decision task of the downstream optimizer [Wilder et al., 2019, Elmachtoub and Grigas, 2022]. Despite this observation, no work— to our knowledge—has yet examined the impact of this divergence for distribution shift. In this paper, we demonstrate that worst-case distribution shifts identified by traditional average accuracy-based metrics fundamentally differ from those for the downstream decision task at hand. We introduce a novel framework that employs a hierarchical model structure to identify worst-case distribution shifts in predictive resource allocation settings. This task is more difficult than in standard distribution shift settings because of combinatorial interactions, where decisions depend on the joint presence of individuals in the allocation task. We show that the problem can be reformulated as a submodular optimization problem, enabling efficient approximations, to capture shifts both within and across instances of the optimization problem. We apply our solution to real-world datasets in public service settings, providing empirical evidence that worst-case shifts for one metric often significantly diverge from worst-case distributions for other metrics.

关键词：

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30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：