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

4,706 篇 会议
641 篇 期刊文献
3 篇 学位论文

馆藏范围

5,350 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,487 篇 工学
- 823 篇 电气工程
- 765 篇 计算机科学与技术...
- 319 篇 信息与通信工程
- 238 篇 控制科学与工程
- 159 篇 软件工程
- 126 篇 机械工程
- 94 篇 仪器科学与技术
- 40 篇 电子科学与技术（可...
- 31 篇 交通运输工程
- 15 篇 航空宇航科学与技...
- 11 篇 测绘科学与技术
- 11 篇 生物医学工程（可授...
- 10 篇 土木工程
- 9 篇 网络空间安全
- 7 篇 材料科学与工程（可...
- 4 篇 动力工程及工程热...
- 4 篇 矿业工程
- 4 篇 石油与天然气工程
- 4 篇 核科学与技术
161 篇 理学
- 68 篇 系统科学
- 54 篇 数学
- 19 篇 生物学
- 17 篇 物理学
- 9 篇 统计学（可授理学、...
- 5 篇 地球物理学
- 4 篇 地理学
100 篇 管理学
- 98 篇 管理科学与工程(可...
49 篇 医学
- 45 篇 临床医学
38 篇 文学
- 37 篇 新闻传播学
7 篇 艺术学
- 7 篇 设计学（可授艺术学...
6 篇 农学
2 篇 教育学
1 篇 军事学

主题

5,350 篇 inference algori...
534 篇 computational mo...
409 篇 fuzzy systems
402 篇 algorithm design...
386 篇 fuzzy logic
382 篇 bayesian methods
370 篇 computer science
334 篇 training
330 篇 neural networks
302 篇 approximation al...
292 篇 bayes methods
229 篇 optimization
225 篇 clustering algor...
217 篇 signal processin...
211 篇 data mining
207 篇 fuzzy sets
203 篇 heuristic algori...
193 篇 prediction algor...
192 篇 accuracy
185 篇 feature extracti...

机构

15 篇 school of electr...
11 篇 university of ch...
10 篇 school of comput...
10 篇 zhejiang univ co...
9 篇 tsinghua univers...
9 篇 purple mt labs p...
9 篇 national univers...
8 篇 microsoft resear...
8 篇 university of mi...
7 篇 department of co...
7 篇 tianjin univ col...
7 篇 department of el...
7 篇 university of so...
7 篇 department of au...
7 篇 tsinghua univ de...
6 篇 ibm thomas j. wa...
6 篇 nanyang technol ...
6 篇 university of so...
6 篇 department of el...
6 篇 department of co...

作者

8 篇 pushmeet kohli
7 篇 li cheng
7 篇 edward r. doughe...
7 篇 wei li
7 篇 xiaodong wang
7 篇 t.s. huang
7 篇 erik b. sudderth
7 篇 a. taylan cemgil
7 篇 p. baranyi
7 篇 nizar bouguila
6 篇 simon godsill
6 篇 alan s. willsky
6 篇 hui wang
6 篇 ying wu
6 篇 wang wei
6 篇 s. suresh
6 篇 chen yongxin
6 篇 yang xu
6 篇 luca benini
6 篇 viktor k. prasan...

语言

5,287 篇 英文
51 篇 其他
11 篇 中文
1 篇 西班牙文

检索条件"主题词=Inference algorithms"

共 5350 条记录，以下是151-160 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：

ReVerie: Contemplating Agency and Truth in Al-assisted Immersive Dream Reliving

ReVerie: Contemplating Agency and Truth in Al-assisted Immer...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Pinyao Liu Keon Ju M. Lee Independent Artist-Researcher School of Interactive Arts + Technology Simon Fraser University

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

ReVerie AI installation explores the scientific concept of dream reliving. Visitors engage in a ritualistic act of whispering their dreams. Each dream transcription and corresponding visualization are temporarily stored in the memory of the AI system. After that, the ReVerie AI system makes an inference from this memory to generate a shared, evolving A/V experience, where participants fly through interconnected dream objects in a virtual space. At its core, ReVerie challenges the capacity of technology to authentically represent the intangible and private terrain of dreams. By inviting participants to contribute whispered dreams that are algorithmically transformed into 3D dream objects, ReVerie pushes them to confront whether such digitally synthesized representations can capture the true essence of our subconscious—or if they craft new forms of detachment or control over personal narratives instead.

关键词： Visualization Three-dimensional displays Art Generative AI Conferences Virtual reality User interfaces inference algorithms

来源：评论

学校读者我要写书评

暂无评论

An Improved Serial IMPLY Adder Algorithm for Efficient Neural Network Applications

An Improved Serial IMPLY Adder Algorithm for Efficient Neura...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Fabian Seiler Nima TaheriNejad Technische Universität Wien (TU Wien) Austria Heidelberg University Germany

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

Memristive systems are one of the most promising candidates for a post-CMOS era. They are small, energy-efficient, and are ideal targets for In-Memory Computation (IMC) via stateful logic. As adders are critical building blocks for any computing systems, improving them is an essential design goal. With the rise of Artificial Intelligence (AI), providing memristive adders that are optimized for Neural Networks (NNs) is extremely important. For this, we propose a Material Implication (IMPLY)-based adder algorithm in the serial topology that can preserve the weights in memory, which was not addressed in the State-of-the-Art (SoA). Our approach is 20% - 23% faster and requires 1% - 12% less energy when the adder is used repeatedly. We propose a flowchart for IMPLY-based algorithms that can represent the state changes of individual memristors and apply it to our adder. We embed our adder in a shift-and-add multiplier and evaluate the potential gains on the 8-bit quantized ResNet18. Our approach is up to 17% more energy-efficient and requires up to 20% fewer cycles for the inference than SoA adder.

关键词： Flowcharts Visualization Network topology Memristors inference algorithms Energy efficiency Topology Logic Artificial intelligence Adders

来源：评论

学校读者我要写书评

暂无评论

Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation

Instance-Warp: Saliency Guided Image Warping for Unsupervise...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Shen Zheng Anurag Ghosh Srinivasa G. Narasimhan Carnegie Mellon University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Driving is challenging in conditions like night, rain, and snow. Lack of good labeled datasets has hampered progress in scene understanding under such conditions. Unsupervised Domain Adaptation (UDA) using large labeled clear-day datasets is a promising research direction in such cases. However, many UDA methods are trained with dominant scene backgrounds (e.g., roads, sky, sidewalks) that appear dramatically different across domains. As a result, they struggle to learn effective features of smaller and often sparse foreground objects (e.g., people, vehicles, signs). In this work, we improve UDA training by applying in-place image warping to focus on salient objects. We design instance-level saliency guidance to adaptively oversample object regions and undersample background areas, which reduces adverse effects from background context and enhances backbone feature learning. Our approach improves adaptation across geographies, lighting, and weather conditions, and is agnostic to the task (segmentation, detection), domain adaptation algorithm, saliency guidance, and underlying model architecture. Result highlights include +6.1 mAP50 for BDD1OOK Clear → DENSE Foggy, +3.7 mAP50 for BDD1OOK Day → Night, +3.0 mAP50 for BDD1OOK Clear → Rainy, and +6.3 mIoU for Cityscapes → ACDC. Besides, Our method adds minimal training memory and no additional inference latency. Code is available at https://***/ShenZheng2000/Instance-Warp.

关键词： Training Representation learning Geography Image segmentation Rain Snow Roads Lighting inference algorithms Meteorology

来源：评论

学校读者我要写书评

暂无评论

LGNet: Linear Graph Representation for Efficient Cold-Start Recommendations

LGNet: Linear Graph Representation for Efficient Cold-Start ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhenglong Li Ruiqi Luo Bangchao Wang Lin Li Xian Zhong School of Computer Science and Artificial Intelligence Wuhan Textile University Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Convolutional Networks (GCNs) demonstrate significant potential in recommendation systems but face difficulties with the cold-start problem, especially in integrating new nodes during inference. The typical solution leverages meta-learning for few-shot learning, though it often fails to fully capture collaborative filtering between nodes. In this paper, we revisit the node embedding propagation algorithm in GCNs, emphasizing the importance of collaborative filtering and elucidating the relation between high-order and low-order embeddings. Given the substantial interaction data required for training recommendation models, maintaining a simple model structure remains crucial. To address these challenges, we propose the Linear Graph Network (LGNet), which theoretically compresses multi-layer GCNs into a single layer, enabling the embedding of new nodes during inference. Experimental results on benchmark datasets for link prediction and user cold-start tasks demonstrate that LGNet outperforms existing methods. The code will be available at https://***/kunbeibei/LGNet.

关键词： Training Metalearning Collaborative filtering Signal processing algorithms Predictive models Prediction algorithms Data models inference algorithms Speech processing Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Labeling for Enhanced User Privacy in Approximate Machine Unlearning

Pseudo-Labeling for Enhanced User Privacy in Approximate Mac...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shunichi Watanabe Artificial Intelligence Laboratory Fujitsu Limited Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper presents an effective pseudo-labeling method for machine unlearning, focusing on protecting user privacy. Recent research predominantly focused on modifying the weights of pre-trained models to approximate exact unlearning. We study the impact of pseudo-labeling methods and propose two novel algorithms for approximate unlearning. Our approach aims to imitate the inference errors and behaviors that arise from exact unlearning of a subset of the target data to be forgotten. To identify the data within the forget set where inferences tend to shift in the wrong direction, we conduct comparative analyses using a pre-trained model, a simple fine-tuning model, and a simple scratch model. We use identified data along with incorrect labels derived from the wrong direction for pseudo-labeling. Experimental evaluations show that our method achieves superior performance in protecting user privacy, demonstrating enhanced forgetting rates and particularly robust defense against membership inference attack.

关键词： Training Performance evaluation Privacy Analytical models Signal processing Data models Robustness inference algorithms Speech processing Research and development

来源：评论

学校读者我要写书评

暂无评论

VisiCompanion: Comparative Analysis of Yolov8 and Yolov9

VisiCompanion: Comparative Analysis of Yolov8 and Yolov9

引用

Disruptive Technologies (ICDT), International Conference on

作者： Payal Chhabra Tanmay Arora Vibhore Jain Neeraj Gandhi Swapnil Bhatnagar Nitin Arora Department of (CSE-AIML) KIET group of institutions Ghaziabad India Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

There are approximately 21 million visually im-paired individuals who depend on other people for their basic work. This research adds to the current understanding of assistive technology by introducing a method for choosing and optimizing the best object detection models suited for accessi-bility environments. This research enhances the Visicompanion functions and assists visually impaired individuals in doing crucial daily tasks independently by selecting a suitable model. This research compares the analysis of two models i.e. Y oLov8 [1] and YOLOV9 [2] and identifies which algorithm is best for the application. YOLOv8 is known for its rapid inference speed which is beneficial for real-time systems whereas YOLOv9 introduces advanced detection capability that improves accuracy but may increase problems for processing time and computational resource requirements. This research uses evaluation metrics like precision, recall, size of model, and resource utilization across different hardware configurations. The results showed thatYOLOv9 is slightly better than YOLOv8 with mAP reaching 95% and precision 96.8%.

关键词： Measurement Computer vision Computational modeling Object detection Assistive technologies Real-time systems inference algorithms Hardware Resource management Disruptive technologies

来源：评论

学校读者我要写书评

暂无评论

Conventional and Intelligent Control Schemes for Handling A Helicopter's Pitch Axis

Conventional and Intelligent Control Schemes for Handling A ...

引用

Advances in Computer Science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Abhishek Chaudhary Electrical Engineering Department Delhi Technological University DTU New Delhi India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

In this paper, a comparative study of conventional LQR controller, optimized PID controller and intelligent Fuzzy logic controller is demonstrated while achieving the desired pitch axis trajectories of a 2-DOF helicopter system. During this process, TLBO optimized PID controller is used to track down the trajectory angle of pitch axis of helicopter system and this performance is compared with inference rules of fuzzy system and a conventional LQR controller. The membership function parameters, exploration - exploitation scheme of optimization algorithm are discussed while addressing the problem of trajectory tracking. The parameter tuning and stable response of pitch axis of helicopter model is achieved on MATLAB/Simulink platform, on which the comparison is accomplished through time response analysis.

关键词： Fuzzy logic Trajectory tracking Helicopters Mathematical models inference algorithms Trajectory Time factors Optimization Tuning Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

algorithms for fuzzy inference and tuning in the fuzzy inference software FINEST

Algorithms for fuzzy inference and tuning in the fuzzy infer...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： T. Arnould S. Tano T. Miyoshi Y. Kato T. Oyama A. Bastian M. Umano Laboratory for International Fuzzy Engineering Research Yokohama Japan Osaka University Toyonaka Osaka Japan

In this paper, we explain the algorithms used in FINEST, the Fuzzy inference Environment Software with Tuning developed at LIFE (Laboratory for International Fuzzy Engineering Research). The research themes and associated algorithms were defined to palliate the insufficiencies of usual inference methods and come naturally from the formulation of fuzzy "if... then..." rules. In particular, enhanced versions of combination operators, implication functions and aggregation operators are proposed, as well as a mechanism to tune the parameters used in the definition of the knowledge used in the system. Finally, one definition and formulation of backward reasoning with fuzzy "if... then..." rules is proposed.< >

关键词： Software algorithms inference algorithms Fuzzy reasoning Fuzzy systems Natural languages Fuzzy sets Systems engineering and theory Uncertainty Logic Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Mining large graphs: algorithms, inference, and discoveries

Mining large graphs: Algorithms, inference, and discoveries

引用

International Conference on Data Engineering

作者： U Kang Duen Horng Chau Christos Faloutsos School of Computer Science Carnegie Mellon University Pittsburgh PA USA

How do we find patterns and anomalies, on graphs with billions of nodes and edges, which do not fit in memory? How to use parallelism for such terabyte-scale graphs? In this work, we focus on inference, which often corresponds, intuitively, to “guilt by association” scenarios. For example, if a person is a drug-abuser, probably its friends are so, too; if a node in a social network is of male gender, his dates are probably females. We show how to do inference on such huge graphs through our proposed HADOOP Line graph Fixed Point (HA-LFP), an efficient parallel algorithm for sparse billion-scale graphs, using the HADOOP platform. Our contributions include (a) the design of HA-LFP, observing that it corresponds to a fixed point on a line graph induced from the original graph; (b) scalability analysis, showing that our algorithm scales up well with the number of edges, as well as with the number of machines; and (c) experimental results on two private, as well as two of the largest publicly available graphs - the Web Graphs from Yahoo! (6.6 billion edges and 0.24 Tera bytes), and the Twitter graph (3.7 billion edges and 0.13 Tera bytes). We evaluated our algorithm using M45, one of the top 50 fastest supercomputers in the world, and we report patterns and anomalies discovered by our algorithm, which would be invisible otherwise.

关键词： Equations Algorithm design and analysis Belief propagation inference algorithms Data mining Convergence Scalability

来源：评论

学校读者我要写书评

暂无评论

Matrix-vector algorithms of local posteriori inference in algebraic Bayesian networks on ideal of disjuncts

Matrix-vector algorithms of local posteriori inference in al...

引用

International Conference on Soft Computing and Measurements (SCM)

作者： Andrey A. Zolotin Ekaterina A. Malchevskaia Computer Science Department St. Petersburg State University St. Petersburg Russia St. Petersburg State University Theoretical and Interdisciplinary Computer Science Lab SPIIRAS St. Petersburg Russia

ISBN: (纸本)9781467389204

An alternative mathematical model of knowledge pattern is described in the article. The calculation of transition matrix from the probability estimates of ideal of disjuncts to probability estimates of ideal of conjuncts and quanta propositions are proposed. The matrix-vector notation of posteriori inference equations for knowledge patterns over ideal of disjuncts is given. Obtained results are applied to the posteriori inference equations for knowledge patterns with uncertain probability estimates.

关键词： Mathematical model Bayes methods Probabilistic logic inference algorithms Linear programming Computer science

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 << < 12 13 14 15 16 17 18 19 20 21 > >>

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：