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：

Detecting Conceptual Abstraction in LLMs 30

Detecting Conceptual Abstraction in LLMs

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Regneri, Michaela Abdelhalim, Alhassan Laue, Sören Universität Hamburg Dept. of Computer Science Machine Learning Research Group Hamburg Germany

ISBN: (纸本)9782493814104

We present a novel approach to detecting noun abstraction within a large language model (LLM). Starting from a psychologically motivated set of noun pairs in taxonomic relationships, we instantiate surface patterns indicating hypernymy and analyze the attention matrices produced by BERT. We compare the results to two sets of counterfactuals and show that we can detect hypernymy in the abstraction mechanism, which cannot solely be related to the distributional similarity of noun pairs. Our findings are a first step towards the explainability of conceptual abstraction in LLMs. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： abstraction attention explainability transformers

来源：评论

学校读者我要写书评

暂无评论

Digital Halftoning via Mixed-Order Weighted ΣΔ Modulation

Digital Halftoning via Mixed-Order Weighted ΣΔ Modulation

引用

2023 International Conference on Sampling Theory and Applications, SampTA 2023

作者： Krahmer, Felix Veselovska, Anna Technical University of Munich and Munich Center for Machine Learning Dept. of Mathematics & Munich Data Science Institute Garching/Munich Germany

ISBN: (纸本)9798350328851

In this paper, we propose 1-bit weighted Σ quantization schemes of mixed order as a technique for digital halftoning. These schemes combine weighted Σ schemes of different orders for two-dimensional signals so one can profit both from the better stability properties of low order schemes and the better accuracy properties of higher order schemes. We demonstrate that the resulting mixed-order Σ schemes in combination with a padding strategy yield improved representation quality in digital halftoning as measured in the Feature Similarity *** empirical results are complemented by mathematical error bounds for the model of two-dimensional bandlimited signals as motivated by a mathematical model of human visual perception. © 2023 IEEE.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Internet of Animal Health Things (IoAHT) Framework for Clinical Mastitis Detection in Dairy Cows 1

Internet of Animal Health Things (IoAHT) Framework for Clini...

引用

1st International Conference on Recent Advances in Information Technology for Sustainable Development, ICRAIS 2023

作者： Ankitha, K. Venugopala, P.S. Kunder, Harish Shetty, Ankitha NMAMIT Nitte Dept. of Artificial Intelligence and Data Science Karkala India Alvas Institute of Engineering and Technology Dept. of Artificial Intelligence and Machine Learning Moodbidri India

ISBN: (纸本)9798350306637

The Earth serves as a shared habitat not just for humans but also for an array of animal species and organisms. Throughout history, animals have played a crucial role in preserving the natural ecosystem balance and meeting diverse human needs. They contribute significantly to various sectors, such as Agriculture, Dairy, Poultry, and animal husbandry, thus bolstering a country's economy. Human responsibility lies in ensuring the well-being of these animals, which is overseen by Veterinary science. In India, a major milk and milk product producer, the dairy industry actively contributes to the nation's economy. Among the primary milk sources-cows, buffaloes, goats, and sheep-cows hold a revered place in different faiths. Particularly in the dairy industry, cows are vital for milk production. However, monitoring cow health poses challenges. Clinical Mastitis, an inflammation affecting cows' mammary glands, hampers milk production. Automatic milking machines are commonly used, but identifying and segregating mastitis-infected cows from healthy ones remains difficult. The contagious nature of the disease increases the risk of widespread infection among cows. To combat this issue, we propose a solution called the Internet of Animal Health Things (IoAHT), based on the Internet of Things (IoT). IoAHT employs IoT technology for animal health, aiming to accurately identify cases of clinical mastitis in cows. The implementation of IoAHT has the potential to revolutionize health monitoring in the dairy industry, safeguarding cow well-being and ensuring sustainable milk production. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Noisy Recovery in Unlimited Sampling via Adaptive Modulo Representations

Noisy Recovery in Unlimited Sampling via Adaptive Modulo Rep...

引用

2024 International Workshop on the Theory of Computational Sensing and its Applications to Radar, Multimodal Sensing and Imaging, CoSeRa 2024

作者： Patricio, Felipe Pagginelli Catala, Paul Krahmer, Felix Tu Munich Dept. of Mathematics Garching Germany Ibmi Helmholtz Munich Neuherberg Germany Institute Tu Munich Munich Center for Machine Learning Dept. of Mathematics&Munich Data Science Garching Germany

ISBN: (纸本)9798350365504

Recent works put forth the Unlimited Sensing Framework (USF), a novel approach to analog-to-digital conversion for high dynamic range sensing. It addresses the saturation phenomenon that commonly arises when physical measurements exceed the dynamic range of a sensor, yielding permanent loss of the input data. However, the USF still has some limitations when dealing with random noise. In the present paper, we propose a novel iterative method to tackle unlimited sensing in a noisy setting. In one step, our approach applies local transformations of the range to remove strong artifacts caused by the noise on local subdivisions of the domain. In the following step, the signal is then approximated via a least squares method. These two types of steps are then alternated. We illustrate the performances of our algorithm in high noise regime. © 2024 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Social Distancing Detection AI System using YOLO

Social Distancing Detection AI System using YOLO

引用

2023 International Conference on Computer, Electronics and Electrical Engineering and their Applications, IC2E3 2023

作者： Karthiga, M. Kavitha, D. Coimbatore Institute of Technology Dept of Artificial Intelligence and Data Science Coimbatore India Coimbatore Institute of Technology Dept. of Artificial Intelligence and Machine Learning Coimbatore India

ISBN: (纸本)9798350338003

The number of reported COVID-19 cases has once again increased due to the recent spread of the H3N2 virus. Even with vaccinations and medications, social distancing remains the most effective way to prevent the spread of these viruses. To address this issue, this paper proposes an automated system for monitoring social distancing in public places. The system utilizes a YOLOv3 object detection model to detect pedestrians in video frames captured by a camera. The frames are then converted to a top-down perspective to measure the distances between individuals in a 2D plane. If any individuals are too close to each other, the system displays a warning by highlighting them with a red frame and a red line. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Optimizing CNNs for Leaf Disease Detection: A Comparative Analysis of Algorithms, Activation functions, and Performance Metrics

Optimizing CNNs for Leaf Disease Detection: A Comparative An...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Nitisha, S. Mohith, N. Vinay, R. Agarwal, Monika Sinha, Aparajita Mokshitha, M. Dayananda Sagar University Dept. Artificial Intelligence and Machine Learning Bangalore India National Institute of Technology Dept. Computer Science Engineering Agartala India

ISBN: (纸本)9798331540821

Agriculture plays an important role in ensuring food security. However, the emergence of plant diseases causes significant economic losses. The routine method of detecting crop diseases is time consuming, requires technical skill and can be inaccurate, especially when new diseases are introduced. To solve these problems, we present a new and effective method for the early identification of leaf diseases using computer vision and machine learning. Extensive testing has been done on the widely used Plant Village dataset to ensure accurate findings. Our plans focus on disease diagnosis and classification. This study demonstrates the pros and drawbacks of this method. The testing process includes data collection, data training, feature extraction, model testing, and classification. The main processing techniques include image acquisition, image preprocessing, extraction and the use of neural networks. Combining computer vision and machine learning, our approach holds great promise for efficient and reliable detection of crop diseases. This has important implications for improving disease control, reducing economic losses and increasing food security. © 2024 IEEE.

关键词： Agriculture Classification CNN Computer Vision Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Understanding Red Wine Quality with Feature Importance in machine learning and Explainable AI 15

Understanding Red Wine Quality with Feature Importance in Ma...

引用

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

作者： John, Ayain Damodar, Navya Mohith, N. Vijayan, Bharathy Dayananda Sagar University Dept. Artificial Intelligence and Machine Learning Bangalore India Dayananda Sagar University Dept. Computer Science Engineering Bangalore India

ISBN: (纸本)9798350370249

The research work investigates the factors that influence the quality of red wine and how they contribute to positive outcomes. It uses machine learning techniques like Support Vector machines (SVM) and K-nearest neighbors (KNN) to classify and assess red wine quality data. Traditionally, red wine quality has been evaluated subjectively, which presents challenges. machine learning algorithms offer an objective alternative. This study compares SVM and KNN algorithms in assessing red wine quality and aims to determine the crucial attributes that affect its quality. To evaluate the classification performance of different machine learning algorithms, metrics like specificity, sensitivity, selectivity, and F1 measure are used. Additionally, grid search algorithms are employed for parameter optimization. In the red wine datasets, the Support Vector machine (SVM) model obtains an accuracy rate of 89%, surpassing the K-Nearest Neighbors (KNN) model's accuracy rate of 87%, especially regarding predictive specificity. Furthermore, using grid search algorithms improves the overall performance of the classifiers. This study highlights the effectiveness of machine learning in assessing red wine quality, providing valuable information for producers to optimize wine production processes and ensure high-quality products for consumers. © 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

Transformer based Compressed data Recovery for Efficient data Collection in Wireless Sensor Networks

Transformer based Compressed Data Recovery for Efficient Dat...

引用

2024 IEEE Students Conference on Engineering and Systems, SCES 2024

作者： Balaji, V.S. Sekar, K. Devendar Rao, B. Dheepa, T. Rajalakshmi Engineering College Dept. of Artificial Intelligence and Machine Learning Chennai India Kongunadu College of Engineering and Technology Dept. of Computer Science and Engineering Tiruchirappalli India

ISBN: (数字)9798350374711

ISBN: (纸本)9798350374711

data collection is challenging in wireless sensor networks (WSNs) since energy consumption remains a significant constraint. Although energy consumption has increased, most data collection methods incur excessive computation overhead. Compressive sensing is used to minimize the number of sensing samples with a suitable sparse basis. A novel Transformer neural network-based compressed data recovery (TCDR) method has been proposed for extracting temporal correlation structures from compressed signals and reconstructing them with high accuracy. The compressed signal is forwarded to the base station through multi-hop communication. The base station uses an attentionbased Transformer Neural Network (TNN) to recover the compressed signal. This model provides greater energy saving performance than the other baseline models considered for evaluation, which are 5.23 percent, 6.82 percent, 10.26 percent, and 11.47 percent, respectively. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Vision: A Comprehensive Review of Computer Vision in AI and ML

Unveiling the Vision: A Comprehensive Review of Computer Vis...

引用

2024 International Conference on Advances in data Engineering and Intelligent Computing Systems, ADICS 2024

作者： Laad, Meena Maurya, Ratan Saiyed, Najeeb Symbiosis Institute Of Technology Dept. Of Applied Science Maharashtra Pune India Symbiosis Institute Of Technology Dept. Of Artificial Intelligence And Machine Learning Maharashtra Pune India

ISBN: (纸本)9798350364828

In the era of rapid technological advancement, Computer Vision has emerged as a transformative force, reshaping the landscape of Artificial Intelligence (AI) and machine learning (ML). This comprehensive review paper aims to delve into the intricate evolution, methodologies, applications, challenges, and future trajectories of Computer Vision. Moving beyond a mere exploration of technical intricacies, our objective is to present a holistic narrative that encapsulates the profound impact of computer Vision on AI and ML and its repercussions across society. The journey begins by traversing the philosophical and historical roots of Computer Vision, unraveling the threads that connect human visual perception to the development of artificial vision. By exploring the historical evolution from early image processing to the current era of deep learning, we seek to elucidate the intellectual milestones that have shaped the field. Methodologically, this paper navigates through both traditional approaches and contemporary deep learning paradigms. It dissects traditional methods, emphasizing their enduring relevance and influence on modern Computer Vision applications. In parallel, exploring deep learning delves into established architectures all the nuanced impact of design choices on interpretability and explain ability. Applications form a cornerstone of our review, with an enriched focus on case studies that spotlight the transformative influence of Computer Vision. Beyond the traditional domains of image recognition, we delve into the healthcare renaissance, where Computer Vision contributes to diagnostics, drug discovery, and personalized medicine. Furthermore, we explore its role in smart cities, extending beyond surveillance to urban planning, traffic management, and environmental monitoring. © 2024 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Diversity Seeking Techniques for Red-Teaming Large Language Models

Diversity Seeking Techniques for Red-Teaming Large Language ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Lee, Seokhan Ku, Bonhwa Ko, Hanseok Dept. Computer Science and Engineering Korea University Seoul Korea Republic of Machine Learning Big Data Institute Korea University Seoul Korea Republic of Dept. Electrical and Computer Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798350368741

In this paper, we present new techniques for increasing the diversity of red-teaming prompts generated by automated machine learning-based methods, thereby enabling the discovery of more vulnerabilities in large language models. Using reinforcement learning to train models to output effective prompts for this task results in the models converging deterministically to a single output. Our first technique, which we term Defender, acts by blocking the reward signal for prompts that have already been discovered, thus making what was a stationary problem into a non-stationary problem that compels the reward maximizing algorithm to continually seek new prompts. Our second technique, Teamplay, trains two prompt generation models in tandem and adds the KL divergence between them to the reward in order to make them search in disparate regions of the space of prompts. Our techniques are shown experimentally to increase the effectiveness and diversity of prompts generated by existing reinforcement learning baselines. © 2025 IEEE.

关键词： AI safety large language models red-teaming reinforcement learning toxicity

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：