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

1,577 篇 会议
1 篇 期刊文献

馆藏范围

1,578 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

897 篇 工学
- 774 篇 计算机科学与技术...
- 531 篇 软件工程
- 251 篇 信息与通信工程
- 193 篇 控制科学与工程
- 131 篇 电气工程
- 84 篇 网络空间安全
- 77 篇 生物医学工程（可授...
- 76 篇 安全科学与工程
- 64 篇 交通运输工程
- 62 篇 生物工程
- 55 篇 电子科学与技术（可...
- 45 篇 动力工程及工程热...
- 42 篇 仪器科学与技术
- 42 篇 石油与天然气工程
- 41 篇 光学工程
304 篇 理学
- 164 篇 数学
- 81 篇 生物学
- 73 篇 统计学（可授理学、...
- 60 篇 物理学
- 37 篇 系统科学
- 33 篇 化学
268 篇 管理学
- 204 篇 管理科学与工程(可...
- 106 篇 图书情报与档案管...
- 84 篇 工商管理
- 35 篇 公共管理
114 篇 医学
- 79 篇 临床医学
- 77 篇 公共卫生与预防医...
- 63 篇 基础医学(可授医学...
52 篇 法学
- 49 篇 社会学
39 篇 经济学
- 39 篇 应用经济学
18 篇 文学
15 篇 教育学
11 篇 农学
2 篇 军事学
1 篇 艺术学

主题

193 篇 data models
158 篇 accuracy
153 篇 computational mo...
92 篇 training
87 篇 feature extracti...
87 篇 machine learning
77 篇 predictive model...
69 篇 data mining
68 篇 deep learning
64 篇 real-time system...
58 篇 big data
49 篇 adaptation model...
45 篇 security
44 篇 robustness
41 篇 decision making
40 篇 cloud computing
40 篇 convolutional ne...
36 篇 analytical model...
35 篇 neural networks
35 篇 artificial intel...

机构

14 篇 lovely professio...
7 篇 shandong provinc...
7 篇 key laboratory o...
6 篇 college of mecha...
6 篇 institute of aer...
5 篇 lloyd institute ...
5 篇 college of intel...
5 篇 university of ch...
5 篇 national univers...
5 篇 department of co...
5 篇 shandong fundame...
5 篇 national univers...
5 篇 institute of aer...
4 篇 karnataka bangal...
4 篇 school of comput...
4 篇 chitkara univers...
4 篇 new horizon coll...
4 篇 srm institute of...
4 篇 school of softwa...
4 篇 koneru lakshmaia...

作者

7 篇 nijhawan ginni
5 篇 jeanette miriam ...
5 篇 lu xiaobo
5 篇 singh navdeep
4 篇 nicola franco
4 篇 choudhry mani de...
4 篇 akhil karnam
4 篇 zhang rui
4 篇 yu zhang
4 篇 akshya j.
4 篇 lihui wang
4 篇 qu yuben
4 篇 wang lihui
4 篇 li lei
4 篇 dong chao
4 篇 dutt varun
4 篇 puri chetan
3 篇 yuangan wang
3 篇 junqi luo
3 篇 zhang lei

语言

1,249 篇 英文
328 篇 其他
4 篇 中文

检索条件"任意字段=2024 IEEE International Conference on Cognitive Computing and Complex Data"

共 1578 条记录，以下是1201-1210 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：

Poster: Exploring Explainability Techniques for Large Language Model Classification Predictions

Poster: Exploring Explainability Techniques for Large Langua...

引用

international conference on Distributed computing Systems

作者： Sriya Ayachitula Ardsley High School Ardsley NY USA

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Large Language Models (LLMs), such as OpenAl's GPT series, are fundamental tools in machine learning that excel in various tasks, including in-context learning. However, these models often operate as “black boxes,” offering limited insight into their decision-making processes. This paper addresses the challenge of explainability in LLMs through a novel approach, using simpler linear models like the Passive-Aggressive Classifier (PAC) as an initial jump-start mechanism to teach the LLM various rules using prompt engineering. We extract and analyze pertinent positives (PPs) as explainable rules and formulate Disjunctive Normal Form (DNF) rules. When taught to the LLM, these rules provide a clear and logical explanation of the decision-making process, enhancing the transparency of LLM predictions. Our methodology improves the interpretability of LLM outputs. The findings suggest that even complex LLM decisions can be distilled into understandable logic, facilitating better user comprehension and trust in classification predictions.

关键词： Large language models Decision making Text categorization Training data Machine learning Picture archiving and communication systems Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

Cohabitation of Intelligence and Systems: Towards Self-reference in Digital Anatomies

Cohabitation of Intelligence and Systems: Towards Self-refer...

引用

ieee international conference on Service-Oriented System Engineering, SOSE

作者： Andrea Morichetta Anna Lackinger Schahram Dustdar TU Wien

ISBN: (数字)9798331539580

ISBN: (纸本)9798331539597

The modern computing scenario of the computing Continuum exhibits large and complex applications with heterogeneous requirements running on distributed infrastructure. Still, when it comes to coordinating and controlling such applications and infrastructures, it is common to rely on centralized or ad-hoc solutions. While these approaches are robust, scaling management solutions, managing local changes, and having a holistic perspective can be challenging. Additionally, they could be better suited for addressing new problems in dynamic environments. Therefore, new approaches are needed. In this paper, we present Dict, a novel method for managing the computing Continuum, i.e., the infrastructure and the applications. The proposed approach encompasses a series of modules for automatic management. The core idea is to develop a method for applying the intents coming from the infrastructure and application managers in an autonomic and dynamic way. The modules can communicate through coordinators that take observable inputs and send them back predictions on the next actions to take. These coordinators have the role of summarizing the sensed observation and extracting high-level information in light of the AI advancement that shows how discrete space representation of inputs improves generalization. Thus, they can have models that build their own semantics and “language.” We envision that, through Dict, both the application and the infrastructure management will only have to specify high-level intents and not focus on defining encoded and difficult-to-change strategies.

关键词： Service-oriented systems engineering Semantics data mining Anatomy Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Time-Efficient Distributed Constant Conditional Functional Dependency Discovery Algorithm for data Consistency

A Time-Efficient Distributed Constant Conditional Functional...

引用

ieee Annual international Computer Software and Applications conference (COMPSAC)

作者： Junchao Chen Jian-tao Zhou Xinyu Hao Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology College of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

The accuracy of data analysis depends on data quality, and addressing data consistency issues is a key challenge to improve it. Constant Conditional Functional Dependency (CCFD) is an effective approach that ensures data consistency by enforcing bindings of semantically related values, thus providing quality assurance for data analysis and decision-making processes. However, with the growth of data scale, especially the increasing number of data tuples and attributes, existing single-machine CCFD discovery algorithms face issues of low computational efficiency and lengthy computation time. This paper proposes a time-efficient distributed CCFD discovery algorithm (DCCFD). Through the optimization of data preprocessing and index mapping, the data organization structure is enhanced, laying the foundation for the discovery of CCFDs under distributed conditions. The Spark parallel computing framework is used to partition the dataset, which accelerates the parallel loading and processing of data. Additionally, this algorithm ensures accuracy and processing speed when discovering dependencies by efficiently generating frequent itemsets and verifying CCFDs in parallel. Experiments on multiple real datasets show that, especially with the complex Airline dataset, the DCCFD algorithm not only accurately discovers CCFDs, but also reduces the average running time by 75.64% compared with the preCFDMiner algorithm.

关键词： Accuracy data preprocessing Software algorithms Distributed databases Parallel processing Software Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Construction of a cognitive Graph for Intelligent Manufacturing Robot Behavior

Construction of a Cognitive Graph for Intelligent Manufactur...

引用

Artificial Intelligence, Robotics, and Communication (ICAIRC), ieee international conference on

作者： Xiaoyu Zheng Bin Huang Guohui Tian Kexin Jin School of Control Science and Engineering Shandong University Jinan China

ISBN: (数字)9798331531225

ISBN: (纸本)9798331531232

The forms of tasks in intelligent manufacturing are diverse, and their operating environment is also dynamically changing. Effective knowledge representation and reasoning are key foundations for enhancing robots' understanding and execution capabilities of complex tasks. Therefore, this article constructs a cognitive graph of robot behavior in the field of intelligent manufacturing based on BERT-BiLSTM-CRF. Firstly, based on the multi-level requirements in robotic operation, a robot behavior corpus is constructed, and the robotic behavior ontology layers Task, Skill, Action, Location, Agent (H), and Object are defined to standardize the semantic structure of behavior. Then, using the BERT model to extract language structure and semantic relationship information, deep-level feature representations are obtained from the text; Capture contextual semantic relationships of behavior through the BiLSTM network, and combine the CRF model to globally constrain and optimize the predicted behavior results. Finally, the extracted triplets are stored using neo4j to form a cognitive graph of intelligent manufacturing robot behavior (IMRBCG). The experimental results show that the P, R, and F1-score of the proposed method are 95.51%, 90.66%, and 93.02%, respectively, effectively extracting 8763 behavioral triplets. This cognitive graph provides technical support for the task of the use of planning and collaboration for intelligent manufacturing robots.

关键词： Semantics Collaboration Predictive models Ontologies Feature extraction Manufacturing Planning data mining Robots Context modeling

来源：评论

学校读者我要写书评

暂无评论

Custom Accessors: Enabling Scalable data Ingestion, (Re-)Organization, and Analysis on Distributed Systems

Custom Accessors: Enabling Scalable Data Ingestion, (Re-)Org...

引用

ieee international conference on Big data

作者： Vito Giovanni Castellana Burcu O. Mutlu Ian Di Dio Lavore Jesun Firoz Katherine Wolf Marco Minutoli John Feo Pacific Northwest National Laboratory Richland WA USA Politecnico di Milano Milano Italy

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

The emerging class of high velocity and high volume data analytic workflows comprise interwoven data ingestion, organization, and processing stages, with ingestion and organization steps often contributing comparable or even higher computational costs than actual processing steps. Since complex workflows consist of a variety of phases that view and use data differently, being able to construct efficient, scalable, distributed data structures (arrays, vectors, sets, maps, and multi-maps) is essential and requires custom methods to extend and shrink containers, analyze and position data, and, maintain globally-consistent meta-data. In this paper, we propose a novel data-structure access paradigm based on the concept of Accessors. At a high level, accessors are customizable callable objects that can modify the behavior of insert, read, update, and delete operations for distributed containers while preserving atomicity guarantees. Accessors provide a very clean and natural way to implement a variety of programming patterns, e.g., conditional insertion/deletion and cascading computations, which would be otherwise hard (or even impossible) to express in parallel and distributed settings without using locks. We demonstrate the practicality and usefulness of our approach with two representative use cases and study the performance of these applications on a distributed High-Performance computing system. Our analysis highlights that our proposed abstraction allows for an effective overlapping and concurrent execution of different workflow steps (e.g., data ingestion and analysis), which in a conventional analytics pipeline would execute sequentially, contributing cumulatively to the overall latency.

关键词： Phased arrays data ingestion data analysis High performance computing Pipelines Distributed databases Organizations Containers Programming Vectors

来源：评论

学校读者我要写书评

暂无评论

FLAMINGO: Adaptive and Resilient Federated Meta-Learning against Adversarial Attacks

FLAMINGO: Adaptive and Resilient Federated Meta-Learning aga...

引用

international conference on Distributed computing Systems Workshop

作者： Md Zarif Hossain Ahmed Imteaj Abdur R. Shahid School of Computing Southern Illinois University Carbondale IL USA Security Privacy and Intelligence for Edge Devices Laboratory (SPEED Lab)

ISBN: (数字)9798350354713

ISBN: (纸本)9798350354720

In today’s data-centric world, the synergy between Meta Learning and Federated Learning (FL) signifies a new era of technological advancement, driving rapid adaptation, improved model generalization, and collaborative model training across decentralized networks. This fusion, known as Federated Meta-Learning (FML), emerges as a cutting-edge solution for resource-constrained edge devices, enabling the production of personalized models with limited training data. However, FML navigates a complex terrain, balancing efficiency with security, as adversarial attacks on edge devices pose significant threats. These attacks risk introducing bias and undermining the integrity of model training, a critical concern given the typically sparse data on edge devices. This paper explores the intricate dynamics of FML amidst such adversarial challenges, introducing a novel algorithm, FLAMINGO. FLAMINGO is designed to conduct adversarial meta-training coupling with data augmentation and consistency regularization strategies, thereby strengthening the meta-learner’s defenses against adversarial attacks. This strategic approach not only protects meta-learners against adversarial threats but also prevents overfitting, striving a balance between privacy, security, and technological efficiency, all while optimizing communication costs in the FML landscape. We have released our code on GitHub 1 , which is publicly accessible. 1 https://***/speedlab-git/***

关键词： Training Metalearning Adaptation models Accuracy Heuristic algorithms Computational modeling Training data

来源：评论

学校读者我要写书评

暂无评论

Converting Vocal Performances into Sheet Music Leveraging Large Language Models

Converting Vocal Performances into Sheet Music Leveraging La...

引用

ieee international conference on data Mining Workshops (ICDM Workshops)

作者： Jinjing Jiang Nicole Teo Haibo Pen Seng-Beng Ho Zhaoxia Wang Research and Development Mastercard Singapore Singapore School of Computing and Information Systems Singapore Management University Singapore Singapore School of Electrical and Information Engineering Tianjin University China China AI Institute Global Singapore

ISBN: (数字)9798331530631

ISBN: (纸本)9798331530648

Advanced natural language processing (NLP) models are increasingly applied in music composition and performance, particularly in generating vocal melodies and simulating singing voices. While NLP techniques have been successfully used to analyze vocal performance data, providing insights into performance quality and style, the automatic transcription of vocal performances into sheet music remains a complex challenge. Existing tools for manual transcription are often insufficient due to the intricate dynamics of vocal expression. This study addresses the challenge of automating the conversion of vocal performances into sheet music using a combination of novel techniques, including large language models (LLMs). We present a method that successfully translates vocal audio input into display-ready sheet music. Our findings highlight the strengths and limitations of various approaches, particularly in the transcription of a cappella performances into notes and lyrics. This research contributes to the expanding field of NLP-driven music analysis and showcases the potential of these models to revolutionize vocal transcription in the future.

关键词： Hands Technological innovation Translation Accuracy Large language models Music Manuals Machine learning Natural language processing data mining

来源：评论

学校读者我要写书评

暂无评论

Research and Application Framework for Trusted Circulation of Food Industry data Based on Blockchain and Federated Learning

Research and Application Framework for Trusted Circulation o...

引用

ieee international conference on Blockchain (Blockchain)

作者： Xin Zhang Yan Ren Jiping Xu Cheng Chi School of Computer and Artificial Intelligence Beijing Technology and Business University Beijing China China Academy of information and communication Institute Of Industrial Internet And Internet Of Things Beijing China

ISBN: (数字)9798350351590

ISBN: (纸本)9798350351606

Food is a necessity for human survival. The circulation of data in the food industry possesses characteristics such as a long lifecycle, complex processes, heterogeneous and sensitive information sources, and susceptibility to leakage. The trend of security risks has shifted from frequent occurrences to emerging, sudden, and sporadic outbreaks. Blockchain, as a novel decentralized architecture and distributed computing paradigm, is gradually being applied in the field of food safety. Federated learning can achieve “usable but invisible” data, improving data utilization and processing efficiency while allowing participants to benefit from data sharing. Blockchain ensures the security of the federated learning model sharing process by holding malicious model contributors and nodes accountable, preventing model data tampering. This paper first comprehensively analyzes the literature on blockchain and federated learning. Based on this analysis, combined with the current application status of blockchain in the food industry and the application ideas of federated learning in other industrial sectors, it proposes a research and application framework for trusted data circulation in the food industry based on blockchain and federated learning. The future development trends are also discussed. Research on trusted data circulation in the food industry can help improve the resilience of the entire food industry chain and the realization of the value of data elements.

关键词： Federated learning Statistical analysis Computational modeling Soft sensors Supply chains Food industry Market research

来源：评论

学校读者我要写书评

暂无评论

A Personalized AI Assistant For Intuition-Driven Visual Explorations

A Personalized AI Assistant For Intuition-Driven Visual Expl...

引用

ieee international conference on e-Science and Grid computing

作者： James Hammer Tanner Hobson David Pugmire Scott Klasky Kenneth Moreland Jian Huang Dept. of EECS University of Tennessee Knoxville Knoxville USA CSMD Division Oak Ridge National Laboratory Oak Ridge USA

ISBN: (数字)9798350365610

ISBN: (纸本)9798350365627

Understanding the time-varying magnetic field within a fusion device is critical for the successful design and construction of clean-burning fusion power plants. Poincaré analysis provides a powerful method for the analysis and visualization of magnetic field lines in fusion devices. Current state-of-the-art relies on manually and iteratively generating Poincaré plots from simulation data. Using Poincaré plots in deep analysis is very time consuming because Poincaré plots can be very computationally expensive, especially for a time-varying simulation with thousands of time steps. Further, the visualization results are so complex that only expert users know how to explore, interpret, and control. In addition, collaboration is hampered due to the high barrier to entry. To this end, we contribute Fugent, a reinforcement learning-based agent capable of recommending and evaluating the importance of exploration regions based on training data captured from historic expert user usage. Using Fugent, we show that important regions can be identified and recommended for further exploration. Fugent is open source.

关键词： Training Visualization data visualization Training data Prototypes User experience Robustness

来源：评论

学校读者我要写书评

暂无评论

Defending Against Backdoor Attacks through Causality-Augmented Diffusion Models for dataset Purification 23

Defending Against Backdoor Attacks through Causality-Augment...

引用

23rd ieee international conference on Trust, Security and Privacy in computing and Communications, TrustCom 2024

作者： Lai, Yuefeng Wu, Lizhao Lin, Hui Zhou, Xiaokang Fujian Normal University College of Computer and Cyber Security FuZhou China Kansai University Faculty of Business Data Science Osaka Japan Riken Center for Aip Tokyo Japan

dataset-Based Defense is a common proactive defense method aimed at countering backdoor attacks by filtering and removing poisoned samples from the training dataset. Recent research has utilized diffusion models to purify contaminated samples. However, during both forward and backward denoising processes, the inherent noise and distribution characteristics of the data can also affect the purification of poisoned samples, making the process unreliable. To address this issue, this paper re-examines the purification process from the perspective of causal graphs, revealing how backdoor triggers and noise act as confounding factors, generating false associations between contaminated images and labels. To eliminate this false association, we propose a Causality-Augmented Diffusion Model-Based Defense (CADMBD) method. CADMBD applies multiple iterations of forward noise addition and backward denoising to the data input in the diffusion model. During the backward denoising process, residual calculation and causal layer adjustment are used to eliminate backdoor pathways, thereby establishing a true causal relationship between benign features and labels. Finally, the most suitable generated image is selected as the final purified image based on pixel and feature distances from each iteration. Experimental results demonstrate that CADMBD effectively addresses various complex attacks, significantly enhancing the purification effect while minimizing the impact on benign sample accuracy, outperforming baseline defense methods. © 2024 ieee.

关键词： Image denoising

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158页 << < 117 118 119 120 121 122 123 124 125 126 > >>

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：