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

13,239 篇 会议
188 册 图书
157 篇 期刊文献

馆藏范围

13,583 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

9,037 篇 工学
- 7,539 篇 计算机科学与技术...
- 4,285 篇 软件工程
- 1,624 篇 信息与通信工程
- 1,528 篇 电气工程
- 1,231 篇 控制科学与工程
- 962 篇 生物工程
- 513 篇 机械工程
- 500 篇 生物医学工程（可授...
- 470 篇 电子科学与技术（可...
- 461 篇 动力工程及工程热...
- 326 篇 光学工程
- 308 篇 交通运输工程
- 294 篇 安全科学与工程
- 267 篇 材料科学与工程（可...
- 248 篇 化学工程与技术
3,512 篇 理学
- 2,202 篇 数学
- 1,058 篇 生物学
- 604 篇 物理学
- 582 篇 统计学（可授理学、...
- 472 篇 系统科学
- 241 篇 化学
1,861 篇 管理学
- 1,292 篇 管理科学与工程(可...
- 681 篇 图书情报与档案管...
- 542 篇 工商管理
595 篇 医学
- 497 篇 临床医学
- 406 篇 基础医学(可授医学...
- 223 篇 药学(可授医学、理...
306 篇 教育学
- 296 篇 教育学
251 篇 法学
- 228 篇 社会学
221 篇 经济学
- 219 篇 应用经济学
136 篇 农学
37 篇 军事学
21 篇 文学
6 篇 艺术学

主题

1,319 篇 optimization
1,089 篇 machine learning
1,031 篇 deep learning
501 篇 accuracy
462 篇 reinforcement le...
329 篇 computational mo...
310 篇 machine learning...
290 篇 training
286 篇 feature extracti...
279 篇 support vector m...
255 篇 predictive model...
248 篇 neural networks
239 篇 real-time system...
210 篇 genetic algorith...
204 篇 adversarial mach...
168 篇 convolutional ne...
161 篇 particle swarm o...
154 篇 learning algorit...
143 篇 artificial intel...
142 篇 internet of thin...

机构

46 篇 chitkara centre ...
36 篇 chitkara univers...
30 篇 chitkara univers...
29 篇 the islamic univ...
23 篇 department of co...
19 篇 al-farahidi univ...
18 篇 centre of resear...
17 篇 lloyd institute ...
17 篇 department of co...
15 篇 school of comput...
14 篇 school of comput...
14 篇 gla university d...
13 篇 vishwakarma inst...
12 篇 university of ch...
11 篇 chitkara univers...
10 篇 columbia univers...
10 篇 univ chinese aca...
10 篇 lovely professio...
10 篇 carnegie mellon ...
9 篇 lovely professio...

作者

13 篇 lima jose
13 篇 pereira ana i.
11 篇 wang wei
9 篇 rakesh kumar
9 篇 wang hui
9 篇 de-shuang huang
9 篇 ye jieping
9 篇 varshney neeraj
8 篇 yang tianbao
8 篇 neeraj varshney
8 篇 r. santhana kris...
8 篇 misra sanjay
7 篇 zhang tao
7 篇 zhang lei
7 篇 li li
7 篇 buzdalov maxim
7 篇 wang jian
7 篇 huang heng
7 篇 hu rong
7 篇 yang yang

语言

11,966 篇 英文
1,588 篇 其他
137 篇 中文
1 篇 阿拉伯文
1 篇 西班牙文
1 篇 俄文
1 篇 土耳其文

检索条件"任意字段=4th International Conference on Optimization Learning Algorithms and Applications"

共 13584 条记录，以下是801-810 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：

Safe Advantage Actor-Critic Based on a Pool of Dangerous Samples 4

Safe Advantage Actor-Critic Based on a Pool of Dangerous Sam...

引用

4th international conference on Consumer Electronics and Computer Engineering, ICCECE 2024

作者： Yan, Xin Huang, Zhiqiu Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China

ISBN: (纸本)9798350384062

Reinforcement learning requires agents to interact extensively with the environment, engaging in thorough exploration during the learning process. However, in practical applications, random exploration of the environment often entails significant risks. Taking dangerous actions could potentially lead to catastrophic consequences. Hence, reinforcing safety in reinforcement learning is an essential aspect for its practical implementation. this paper proposes enhancing the Advantage Actor Critic algorithm by introducing a deep Q-network, referred to as the punisher. the Punisher network learns from a pool of dangerous samples and provides a penalty factor to the Actor network. this allows the Actor network to learn while considering both reward and penalty factors. It penalizes actions that might lead to dangerous states, thereby strengthening the traditional Actor Critic framework with safety ***, within the Gym platform's Mountain Car game, this method demonstrates the ability to enhance safety during exploration while sacrificing a certain degree of learning efficiency. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A-eye: Attendance monitoring using face detection and recognition from CCTV footage 4

A-eye: Attendance monitoring using face detection and recogn...

引用

4th international conference on Emerging Smart Technologies and applications (eSmarTA)

作者： Ambre, Nimesh Pitale, Raveena Rao, Prajeet Mote, Hemalata Chavan, Satishkumar Don Bosco Inst Technol Dept Elect & Telecomm Mumbai 400070 Maharashtra India Dwarkadas J Sanghvi Coll Engn Dept Elect & Telecomm Vile Parle W Mumbai 400056 Maharashtra India

ISBN: (纸本)9798350354140;9798350354133

Monitoring and updating attendance records of students is an integral part of activities in schools and colleges. To mitigate the laborious work of keeping attendance records, an automated method of attendance monitoring using face as a biometrics is proposed. In this paper, face detection and recognition for maintaining student attendance using deep learning methodology is presented. Face detection in lowresolution CCTV footage is achieved using the Haar Cascade algorithm with 88.59% detection accuracy. the detection is not limited to frontal face detection. It also has side face selection along with varied illumination situations. these detected faces are then used to create a student face database. the Convolutional Neural Network (CNN) is trained on this face database for student recognition to mark attendance. A total of 60 students' face data is used in this for recognition and updating attendance for 5 subjects. the proposed CNN provided 76% face recognition accuracy for the implemented network.

关键词： Face detection face recognition Haar cascade Convolutional neural network deep learning Closed-circuit television.

来源：评论

学校读者我要写书评

暂无评论

Turbo-Charging Deep learning Methods for Partial Differential Equations 23

Turbo-Charging Deep Learning Methods for Partial Differentia...

引用

4th ACM international conference on AI in Finance (ICAIF)

作者： Buet-Golfouse, Francois Utyagulov, Islam Pahwa, Parth Hill, Peter JPMorgan Chase Decis Sci London England UCL London England

ISBN: (纸本)9798400702402

Solving partial differential equations (PDEs) is a frequent necessity in numerous domains, ranging from complex systems simulation to financial derivatives pricing and continuous-time optimisation tasks. the challenging nature of PDEs, especially in high dimensions or cases involving non-linearities, calls for robust, innovative solutions. this paper leverages a deep neural network methodology, utilizing differential operators and boundary conditions in tandem with sampling techniques and minimising distinct loss terms. the role of physics-inspired neural networks in this approach is also highlighted. Our primary proposition is a Bayesian interpretation, where we address the issue as a hierarchical multi-objective optimisation problem augmented with adaptive sampling. We also introduce a concept of 'curriculum learning,' which parallels control variates, thereby facilitating further variance reduction and the re-utilisation of solutions derived from assorted problems. Our methods notably enhance the speed of convergence and diminish approximation errors. the effectiveness of our strategies is demonstrated through illustrative examples, solidifying their value in practical applications.

关键词： Partial Differential Equations Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Digital Game-based learning Approach to Improve Students' learning Performance of Senior High School Programming Courses 23

A Digital Game-based Learning Approach to Improve Students' ...

引用

4th international conference on Education Development and Studies (ICEDS)

作者： Xu, Xiang Liu, Rui Chen, Qinqin Yang, Hairu China West Normal Univ Dept Educ Technol Inst Educ Nanchong Peoples R China 3 Middle Sch Dechang Cty Xichang Liangshan Prefe Peoples R China

ISBN: (纸本)9798400707506

As an important means to improve teenagers' computational thinking, programming education has been paid more and more attention. But the traditional teaching mode of programming course is boring and abstract, which makes learners lack motivation and enthusiasm for learning. therefore, learning methods based on digital games may be a potential optimization strategy. this paper proposes a learning method based on digital games and conducts a quasi-experimental study in a senior high school in China. the experimental group was placed in a learning method based on digital games to evaluate the effectiveness of the proposed learning method and game learning behavior, while the control group used traditional classroom teaching methods for learning. the results showed that the experimental group was better than the control group in learning experience, learning interest, collaborative learning ability and learning performance. It provides a valuable reference for Game-based programming teaching and research.

关键词： Digital game-based learning Programming education Teaching process

来源：评论

学校读者我要写书评

暂无评论

SimStock : Representation Model for Stock Similarities 23

SimStock : Representation Model for Stock Similarities

引用

4th ACM international conference on AI in Finance (ICAIF)

作者： Hwang, Yoontae Lee, Junhyeong Kim, Daham Noh, Seunghwan Hong, Joohwan Lee, Yongjae Ulsan Natl Inst Sci & Technol Ulsan South Korea Cornell Univ New York South Korea

ISBN: (纸本)9798400702402

In this study, we introduce SimStock, a novel framework leveraging self-supervised learning and temporal domain generalization techniques to represent similarities of stock data. Our model is designed to address two critical challenges: 1) temporal distribution shift (caused by the non-stationarity of financial markets), and 2) ambiguity in conventional regional and sector classifications (due to rapid globalization and digitalization). SimStock exhibits outstanding performance in identifying similar stocks across four real-world benchmarks, encompassing thousands of stocks. the quantitative and qualitative evaluation of the proposed model compared to various baseline models indicates its potential for practical applications in stock market analysis and investment decision-making.

关键词： Similar stocks Self-supervised learning Stock representation Temporal distribution shift Domain generalization

来源：评论

学校读者我要写书评

暂无评论

JaxDecompiler: Redefining Gradient-Informed Software Design 7th

JaxDecompiler: Redefining Gradient-Informed Software Design

引用

7th international conference on optimization and learning

作者： Pochelu, Pierrick Univ Luxembourg FSTM DCS Esch Sur Alzette Luxembourg

ISBN: (纸本)9783031779404;9783031779411

Among numerical libraries capable of computing gradient descent optimization, JAX stands out by offering more features, accelerated by an intermediate representation known as Jaxpr language. However, editing the Jaxpr code is not directly possible. this article introduces JaxDecompiler, a tool that transforms any JAX function into an editable Python code, especially useful for editing the JAX function generated by the gradient function. JaxDecompiler simplifies the processes of reverse engineering, understanding, customizing, and interoperability of software developed by JAX. We highlight its capabilities, emphasize its practical applications especially in deep learning and more generally gradient-informed software, and demonstrate that the decompiled code speed performance is similar to the original.

关键词： Gradient Descent Software Design Decompilation Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Review on Advances in Sentiment Analysis: A Deep learning Approach Using Transformer Based Models 4

A Review on Advances in Sentiment Analysis: A Deep Learning ...

引用

4th international conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Kale, Tejas Vijayrao Mendhe, Sameer Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Maharashtra Wardha India

ISBN: (纸本)9798331523923

A key element of natural language processing is sentiment analysis, which comprises recognizing and understanding opinions and emotions in text. Traditional sentiment categorization methods like machine learning and lexicon-based approaches were made more accurate by deep learning techniques. Transformer-based models that capture long-range relationships through self-attention methods and complicated contextual linkages in text, such as BERT, GPT, RoBERTa, and DistilBERT, have made important contributions to the field. these models perform better than previous methods for multilingual sentiment identification, aspect-based sentiment analysis, and text categorization. However, there are problems like requirement for huge datasets and expensive processing requirements persist. Recent advancements such as lightweight transformer models, multimodal frameworks, and combine efforts of transformer variants like RoBERTa and DistilBERT to improve interpretability address these problems. this study explores the use of RoBERTa-large model for sentiment analysis task using IMDb dataset library containing 50000 movie reviews classified as positive and Negative. RoBERTa-large model achieved accuracy of 96.05% on testing data which shows growing importance of transformer model in NLP applications. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Model for Recognising Handwritten Devanagari Numerals using Machine learning 4

A Novel Model for Recognising Handwritten Devanagari Numeral...

引用

4th international conference on Pervasive Computing and Social Networking (ICPCSN)

作者： Prathima, Ch Arava, Ramprakash Reddy Sevitha, K. Manikanth, G. Vinay, D. Surya, C. Mohan Babu Univ Sch Comp Tirupati Andhra Pradesh India KSRM Coll Engn Dept CSE Kadapa Andhra Pradesh India Sree Vidyanikethan Engn Coll Dept CSSE Tirupati Andhra Pradesh India

ISBN: (纸本)9798350386356;9798350386349

this research study performs a comprehensive comparative analysis aimed at developing effective machine learning models for classifying handwritten Devanagari numerals. the research focuses on evaluating the performance of various models to determine the most accurate classification approach. Initiating with data pre-processing, including feature extraction and normalization, the data is prepared for model training and assessment. A diverse range of machine learning models, from traditional methods like Support Vector Machines (SVM) to advanced techniques such as Random Forests, K-Nearest Neighbors, and Convolutional Neural Networks, are considered for the comparative analysis, ensuring a thorough assessment of classification capabilities. Cross-validation techniques are employed during model training and testing to enhance reliability. Statistical tests are utilized to assess the performance variations among models, enhancing the robustness of the analysis. Visual representations of performance metrics and comparison results offer clear insights. this research study aims to identify the most suitable machine learning model for handwritten Devanagari numeral classification, potentially advancing character recognition systems and linguistic applications.

关键词： Handwritten character recognition Machine learning Support Vector Machine(SVM) Data augmentation Transfer learning Digital document processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Node Classification: Integrating Particle Swarm optimization with Graph Convolutional Networks 4

Enhancing Node Classification: Integrating Particle Swarm Op...

引用

4th international conference on Intelligent Cybernetics Technology and applications, ICICyTA 2024

作者： Nasari, Maulin Pradana, Rilo Chandra Tarigan, Gabriel Asael Masaling, Nikita Ananda Putri Tedjasulaksana, Jeffrey School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

the effectiveness of Graph Neural Networks (GNNs) in processing graph-structured data gained widespread recognition, and these models have applications in a wide range of fields. Even though GNNs have a lot of potential, optimising GNN models for particular tasks is still challenging. Within the scope of this research, a method is presented that combines Particle Swarm optimization (PSO) and Graph Convolutional Networks (GCN) to enhance the performance of node classification. Using the Amazon Computers and Amazon Photo datasets, which are both made up of product nodes that are connected to one another. the methodology includes data preprocessing with PyTorch Geometric, strategic data partitioning, and a robust hyperparameter optimization process using PSO. the modification was able to achieve an accuracy of 88.7% on the Amazon Computers dataset and 94.9% on the Amazon Photo dataset, which is higher than the traditional GCN baselines. Our GCN-PSO model demonstrated significant performance enhancements. these findings highlight the effectiveness of PSO in fine-tuning GCN hyperparameters, which ultimately results in outcomes that are more accurate and efficient. When it comes to improving graph-based data analysis, the research highlights the potential of combining GCNs with optimization techniques such as PSO. this method could be extended to other graph learning challenges in subsequent research, and alternative optimization strategies could be investigated to further push the limits of GNN performance. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Implementation of Optimal Crop Recommendation System using Machine learning algorithms 4

Implementation of Optimal Crop Recommendation System using M...

引用

4th international conference on Expert Clouds and applications, ICOECA 2024

作者： Sanjana, Siram Kumar, K Nithin Satyanarayana, P. Suresh Varma, K.N.V. Anitha, Inumula Krishnan, V. Gokula V. R. Siddhartha Engineering College Department of ECE AP Vijayawada India S.R.K.R. Engineering College Department of ECE A.P Bhimavaram India Department of CSE Tamil Nadu Chennai India

ISBN: (纸本)9798350385793

Agriculture consumes a significant 85% of the world's freshwater resources, a trend expected to persist due to growing population and food demand. To overcome this challenge, developing strategic solutions blending scientific principles and advanced technology are essential. Leveraging machine learning technologies, an innovative model is proposed to minimize crop loss due to adverse weather conditions. the proposed integrated system addresses three critical aspects of agriculture: crop selection, fertilizer recommendations, and automated irrigation. By analyzing various parameters such as pH levels, current weather, and soil nutrients (potassium, phosphorous, nitrogen), the proposed model adeptly selects optimal crops based on various environmental factors. A mobile application translates soil conditions into graphical data for easy interpretation. Evaluation of machine learning algorithms reveals Support Vector Machine (SVM) as the highest accuracy at 95.89%, followed closely by Naïve Bayes (NB) at 95.24%. Decision Tree also performs competitively at 95.05%, while K-nearest Neighbors (K-NN) trails slightly with 93.81% accuracy. these findings depict the efficacy of SVM in accurately classifying datasets, presenting a promising path for addressing water demand in agriculture. © 2024 IEEE.

关键词： Adversarial 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500页 << < 77 78 79 80 81 82 83 84 85 86 > >>

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：