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

29 篇 会议
1 册 图书

馆藏范围

30 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

25 篇 工学
- 23 篇 计算机科学与技术...
- 5 篇 软件工程
- 1 篇 机械工程
- 1 篇 光学工程
3 篇 教育学
- 3 篇 教育学
3 篇 理学
- 2 篇 数学
- 1 篇 物理学
1 篇 文学
- 1 篇 外国语言文学

主题

3 篇 artificial intel...
3 篇 training
2 篇 reinforcement le...
2 篇 e-learning
2 篇 iterative method...
1 篇 localisation
1 篇 big model
1 篇 learning systems
1 篇 inductive infere...
1 篇 pac-bayes bounds
1 篇 solomonoff induc...
1 篇 bridges
1 篇 regression analy...
1 篇 systematic liter...
1 篇 aixi
1 篇 big data
1 篇 image segmentati...
1 篇 boolean function...
1 篇 microscopy
1 篇 e-learning,const...

机构

1 篇 univ kitakyushu ...
1 篇 nanyang technol ...
1 篇 research school ...
1 篇 univ politecn ca...
1 篇 tsinghua univ st...
1 篇 georgia inst tec...
1 篇 university of tu...
1 篇 astar inst infoc...
1 篇 carnegie mellon ...
1 篇 suas educ dev 14...
1 篇 carnegie mellon ...
1 篇 univ london comp...
1 篇 carnegie mellon ...
1 篇 university of tu...
1 篇 univ fed paraiba...
1 篇 max planck inst ...
1 篇 english departme...
1 篇 department of co...
1 篇 univ regina dept...
1 篇 univ london comp...

作者

2 篇 zhdanov fedor
2 篇 zilles sandra
1 篇 vovk vladimir
1 篇 sugiyama mahito
1 篇 uchiya taishi
1 篇 simon hans ulric...
1 篇 noleto jaqueline...
1 篇 doliwa thorsten
1 篇 wei jinliang
1 篇 arici anna
1 篇 li-hsin chang
1 篇 zhang jianwen
1 篇 yu yaoliang
1 篇 gavalda ricard
1 篇 kudo mineichi
1 篇 gresalfi melissa
1 篇 tsuiki hideki
1 篇 yang tianbao
1 篇 yamamoto akihiro
1 篇 moelius iii samu...

语言

29 篇 英文
1 篇 其他

检索条件"任意字段=21st International Conference on Algorithmic Learning Theory, ALT 2010"

共 30 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：

Breakpoints in Iterative Development and Interdisciplinary Collaboration of AI-Driven Automated Assessment 21

Breakpoints in Iterative Development and Interdisciplinary C...

引用

21st international conference on Information Technology Based Higher Education and Training, ITHET 2024

作者： Huang, Xiaoshan Chang, Li-Hsin Veermans, Koen Ginter, Filip University of Turku Department of Teacher Education Turku Finland University of Turku Department of Computing Turku Finland

ISBN: (纸本)9798331516635

The rise of AI in education has led to significant advancements, promoting automated grading to reduce educator workload and to enhance pedagogy. However, its integration raises complex pedagogical, ethical, and technical questions. This systematic review examines the intersection of automated grading tool development and educational assessment through the lens of the activity theory. Our analysis, informed by literature since 2010, reveals a critical need for comprehensive evaluation frameworks addressing the iterative nature of technology development and interdisciplinary collaboration. Key breakpoints in existing studies include oversight of the reliability and validity of assessments, ethical considerations, coherent evaluation rules, interdisciplinary collaboration, and agentive and constructive roles of users. Addressing these issues requires a holistic approach that bridges technical and educational perspectives, fostering trust and supporting meaningful learning outcomes. Enhanced collaboration and ongoing professional development are crucial for creating AI-driven assessments. © 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

Mixed Time-Frame Training for Reinforcement learning

Mixed Time-Frame Training for Reinforcement Learning

引用

international conference on Machine learning and Applications (ICMLA)

作者： Gautham Senthilnathan Computer Science Department Durham University

Reinforcement learning typically only uses one type of environment during training: episodic or non-episodic. In this paper, we propose a novel training technique, Mixed Time-Frame Training, which combines episodic environments and non-episodic environments through training in parallel. This approach takes advantage of the different exploration-exploitation characteristics of the two environment types. We shall benchmark the proposed technique on 10 Atari games with varying levels of exploration difficulty, showing a significant increase in performance. The increase in performance comes with no increase in training frames, algorithmic complexity or computation.

关键词： Training Machine learning algorithms Reinforcement learning Games Benchmark testing Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Breakpoints in Iterative Development and Interdisciplinary Collaboration of AI-Driven Automated Assessment

Breakpoints in Iterative Development and Interdisciplinary C...

引用

international conference on Information Technology Based Higher Education and Training, ITHET

作者： Xiaoshan Huang Li-Hsin Chang Koen Veermans Filip Ginter Department of Teacher Education University of Turku Turku Finland Department of Computing University of Turku Turku Finland

ISBN: (数字)9798331516635

ISBN: (纸本)9798331516642

关键词： Training Bridges Ethics Collaboration Reliability theory Iterative methods Information technology Artificial intelligence Systematic literature review Lenses

来源：评论

学校读者我要写书评

暂无评论

An algorithmic Framework for Malicious Software Detection Exploring structural Characteristics of Behavioral Graphs 20

An Algorithmic Framework for Malicious Software Detection Ex...

引用

21st international conference on Computer Systems and Technologies, CompSystech 2020

作者： Chysi, Alvaro Nikolopoulos, stavros D. Polenakis, Iosif Department of Computer Science and Engineering University of Ioannina Ioannina Greece

ISBN: (纸本)9781450377683

In this paper, we present the development of an algorithmic framework for the behavioral detection of malicious software utilizing a set of measurements to explore the structural characteristics of behavioral graphs. We first present the construction of the Group Relation Graphs produced by a specific type of behavioral graphs, the so called System-call Dependency Graphs obtained through taint-analysis after the execution of a malicious sample. Then, we discuss the utilization of a set of measurements applied to compute the structural characteristics of Group Relation Graphs, namely the application of the Page Rank algorithm on such graphs and the Betweeness Centrality on the vertices of the graph. We present the architecture of our proposed framework and how we deploy the computation of similarity metrics in order to measure the closeness between such characteristics exhibited among malicious and benign samples in order to perform the malware detection process. Finally, we proceed to a series of experiments in order to evaluate through five-fold cross validation the detection ability of our proposed model and prove its potentials against a set of System-call Dependency Graphs to distinguishing malicious from benign software samples. © 2020 ACM.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

HCI Methods and Practices for Audiovisual Systems and Their Potential Contribution to Universal Design for learning: A Systematic Literature Review 13th

HCI Methods and Practices for Audiovisual Systems and Their ...

引用

13th international conference on Universal Access in Human-Computer Interaction (UAHCI) part of the 21st international conference on Human-Computer Interaction (HCI)

作者： Toscano, Rafael M. de Souza, Helder Bruno A. M. da Silva Filho, Sandro G. Noleto, Jaqueline D. Becker, Valdecir Univ Fed Paraiba Informat Ctr Audiovisual Design Res Grp Joao Pessoa Brazil

ISBN: (纸本)9783030235598;9783030235604

Audiovisual production, which was previously mostly investigated by film and television studies, now becomes more comprehensive and can involve aspects of psychology, pedagogy, neuroscience and especially computing. In parallel to this evolution, studies on Universal Access or Universal Design have been expanding their scope for services, technologies and learning processes. This article presents a systematic literature review with the objective of investigating the main uses and applications of Computer Human Interaction (IHC) theories and methods related to the development of audiovisual systems and their possible contributions to Universal Design for learning (UDL). The review contemplates articles from four databases in the period from 2010 to 2018. All 31 articles are classified by the context of the research problems and solutions proposed using principles of the grounded theory, that is, the codification of data through hierarchical categorization, establishment of relation and creation of central categories. These works are divided into three main groups of problems (user interfaces, theoretical and behavioral bases and system application) and solutions (theories and methods, design and evaluation of interactive systems and case studies). HCI state of the art productions and methods using audiovisual systems, i.e. audio and video, multimedia, hypermedia or even multimodal systems, has revealed a scenario of products, devices and interaction methods that have evolved and become more complex over the years. While not working directly with the Universal Design context, the various solutions present results that can benefit the development of learning support systems.

关键词： HCI Audiovisual systems Universal Design for learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion in Social and Information Networks: Research Problems, Probabilistic Models & Machine learning Methods 15

Diffusion in Social and Information Networks: Research Probl...

引用

21st ACM SIGKDD conference on Knowledge Discovery and Data Mining (KDD)

作者： Gomez-Rodriguez, Manuel Song, Le MPI Software Syst Saarbrucken Germany Georgia Inst Technol Atlanta GA 30332 USA

ISBN: (纸本)9781450336642

In recent years, there has been an increasing effort on developing realistic models, and learning and inference algorithms to understand, predict, and influence diffusion over networks. This has been in part due to the increasing availability and granularity of large-scale diffusion data, which, in principle, allows for understanding and modeling not only macroscopic diffusion but also microscopic (node-level) diffusion. To this aim, a bottom-up approach has been typically considered, which starts by considering how particular ideas, pieces of information, products, or, more generally, contagions spread locally from node to node apparently at random to later produce global, macroscopic patterns at a network level. However, this bottom-up approach also raises significant modeling, algorithmic and computational challenges which require leveraging methods from machine learning, probabilistic modeling, event history analysis and graph theory, as well as the nascent field of network science. In this tutorial, we will present several diffusion models designed for fine-grained large-scale diffusion data, present some canonical research problem in the context of diffusion, and introduce state-of-the-art algorithms to solve some of these problems, in particular, network estimation, influence estimation and influence control.

关键词： information propagation information networks diffusion networks social networks social influence

来源：评论

学校读者我要写书评

暂无评论

Petuum: A New Platform for Distributed Machine learning on Big Data 15

Petuum: A New Platform for Distributed Machine Learning on B...

引用

21st ACM SIGKDD conference on Knowledge Discovery and Data Mining (KDD)

作者： Xing, Eric P. Ho, Qirong Dai, Wei Kim, Jin Kyu Wei, Jinliang Lee, Seunghak Zheng, Xun Xie, Pengtao Kumar, Abhimanu Yu, Yaoliang Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA ASTAR Inst Infocomm Res Singapore Singapore

ISBN: (纸本)9781450336642

How can one build a distributed framework that allows efficient deployment of a wide spectrum of modern advanced machine learning (ML) programs for industrial-scale problems using Big Models (100s of billions of parameters) on Big Data (terabytes or petabytes)? Contemporary parallelization strategies employ fine-grained operations and scheduling beyond the classic bulk-synchronous processing paradigm popularized by MapReduce, or even specialized operators relying on graphical representations of ML programs. The variety of approaches tends to pull systems and algorithms design in different directions, and it remains difficult to find a universal platform applicable to a wide range of different ML programs at scale. We propose a general-purpose framework that systematically addresses data- and model-parallel challenges in large-scale ML, by leveraging several fundamental properties underlying ML programs that make them different from conventional operation-centric programs: error tolerance, dynamic structure, and nonuniform convergence;all stem from the optimization-centric nature shared in ML programs' mathematical definitions, and the iterative convergent behavior of their algorithmic solutions. These properties present unique opportunities for an integrative system design, built on bounded-latency network synchronization and dynamic load-balancing scheduling, which is efficient, programmable, and enjoys provable correctness guarantees. We demonstrate how such a design in light of ML first principles leads to significant performance improvements versus well-known implementations of several ML programs, allowing them to run in much less time and at considerably larger model sizes, on modestly-sized computer clusters.

关键词： Machine learning Big Data Big Model Distributed Systems theory Data-Parallelism Model-Parallelism

来源：评论

学校读者我要写书评

暂无评论

algorithmic learning theory - 21st international conference, alt 2010, Proceedings

Algorithmic Learning Theory - 21st International Conference,...

引用

21st international conference on algorithmic learning theory, alt 2010

ISBN: (纸本)3642161073

The proceedings contain 27 papers. The topics discussed include: towards general algorithms for grammatical inference;the blessing and the curse of the multiplicative updates;discovery of abstract concepts by a robot;contrast pattern mining and its application for building robust classifiers;optimal online prediction in adversarial environments;an algorithm for iterative selection of blocks of features;Bayesian active learning using arbitrary binary valued queries;approximation stability and boosting;a spectral approach for probabilistic grammatical inference on trees;pagerank optimization in polynomial time by stochastic shortest path reformulation;inferring social networks from outbreaks;compressed learning with regular concept;a lower bound for learning distributions generated by probabilistic automata;and lower bounds on learning random structures with statistical queries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

learning to count with regression forest and structured labels

Learning to count with regression forest and structured labe...

引用

international conference on Pattern Recognition

作者： Luca Fiaschi Ullrich Koethe Rahul Nair Fred A. Hamprecht HCI/IWR Heidelberg Germany

ISBN: (纸本)9781467322164

Following [Lempitsky and Zisserman, 2010], we seek to count objects by integrating over an object density map that is predicted from an input image. In contrast to that work, we propose to estimate the object density map by averaging over structured, namely patch-wise, predictions. Using an ensemble of randomized regression trees that use dense features as input, we obtain results that are of similar quality, at a fraction of the training time, and with low implementation effort. An open source implementation will be provided in the framework of http://***.

关键词： Training Vegetation Microscopy Image segmentation Uncertainty Regression tree analysis Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Bayesian Active learning Using Arbitrary Binary Valued Queries

Bayesian Active Learning Using Arbitrary Binary Valued Queri...

引用

21st international conference on algorithmic learning theory (alt) / 13th international conference on Discovery Science (DS)

作者： Yang, Liu Hanneke, steve Carbonell, Jaime Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Carnegie Mellon Univ Dept Stat Pittsburgh PA 15213 USA Carnegie Mellon Univ Language Technol Inst Pittsburgh PA 15213 USA

We explore a general Bayesian active learning setting, in which the learner can ask arbitrary yes/no questions. We derive upper and lower bounds on the expected number of queries required to achieve a specified expect... 详细信息

ISBN: (纸本)9783642161070

关键词： Active learning Bayesian learning Sample Complexity Information theory

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3页 << < 1 2 3 > >>

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：