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

57,254 篇 会议
184 册 图书

馆藏范围

57,431 篇 电子文献
7 种 纸本馆藏

日期分布

学科分类号

57,042 篇 工学
- 56,774 篇 计算机科学与技术...
- 7,556 篇 控制科学与工程
- 2,464 篇 软件工程
- 2,057 篇 电气工程
- 483 篇 信息与通信工程
- 360 篇 生物医学工程（可授...
- 67 篇 机械工程
- 57 篇 土木工程
- 23 篇 石油与天然气工程
- 18 篇 生物工程
- 15 篇 仪器科学与技术
4,454 篇 理学
- 3,698 篇 数学
- 368 篇 物理学
- 274 篇 生物学
- 53 篇 科学技术史(分学科...
- 52 篇 统计学（可授理学、...
- 22 篇 系统科学
- 18 篇 化学
2,190 篇 医学
- 1,233 篇 基础医学(可授医学...
- 1,065 篇 临床医学
- 36 篇 特种医学
2,181 篇 文学
- 2,178 篇 外国语言文学
1,356 篇 管理学
- 1,257 篇 管理科学与工程(可...
- 84 篇 图书情报与档案管...
1,231 篇 教育学
- 709 篇 教育学
- 507 篇 心理学(可授教育学...
- 15 篇 体育学
57 篇 法学
- 56 篇 社会学
36 篇 艺术学
- 36 篇 音乐与舞蹈学
35 篇 哲学
- 35 篇 哲学
13 篇 经济学
1 篇 农学
1 篇 军事学

主题

1,258 篇 artificial intel...
1,112 篇 machine learning
978 篇 deep learning
919 篇 data mining
780 篇 multi agent syst...
725 篇 semantics
527 篇 classification
510 篇 reinforcement le...
474 篇 learning systems
463 篇 clustering
439 篇 neural networks
415 篇 ontology
353 篇 natural language...
257 篇 computers
249 篇 rough sets
236 篇 fuzzy sets
230 篇 feature selectio...
219 篇 computer circuit...
213 篇 knowledge repres...
205 篇 logic programmin...

机构

191 篇 univ chinese aca...
107 篇 chinese acad sci...
65 篇 harbin inst tech...
63 篇 polish acad sci ...
62 篇 wroclaw univ sci...
59 篇 soochow univ sch...
55 篇 delft univ techn...
53 篇 carnegie mellon ...
48 篇 beijing univ tec...
44 篇 chinese acad sci...
44 篇 shanghai jiao to...
43 篇 tu wien austria
42 篇 univ sci & techn...
41 篇 czech tech univ ...
40 篇 univ ulsan sch e...
39 篇 beijing jiaotong...
38 篇 tsinghua univ de...
38 篇 north carolina s...
37 篇 nanjing univ sta...
36 篇 tsinghua univ sc...

作者

47 篇 gelbukh alexande...
42 篇 wang lei
36 篇 reis luis paulo
35 篇 pelachaud cather...
35 篇 malerba donato
34 篇 liu yang
33 篇 novais paulo
33 篇 cpalka krzysztof
32 篇 li li
30 篇 ricci alessandro
27 篇 lau nuno
26 篇 wang hui
26 篇 napoli amedeo
25 篇 boryczka urszula
25 篇 rutkowski leszek
25 篇 wang jing
25 篇 pluhacek michal
25 篇 bickmore timothy
25 篇 calvo hiram
24 篇 villasenor-pined...

语言

57,321 篇 英文
116 篇 中文
1 篇 丹麦文

检索条件"丛书名=Lecture notes in artificial intelligence,"

共 57438 条记录，以下是4611-4620 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：

Proximal Symmetric Non-negative Latent Factor Analysis: A Novel Approach to Highly-Accurate Representation of Undirected Weighted Networks 1

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Zhong, Yurong Xie, Zhe Li, Weiling Luo, Xin Dongguan Univ Technol Sch Comp Sci & Technol Dongguan Peoples R China

ISBN: (数字)9789819947522

ISBN: (纸本)9789819947515;9789819947522

An undirected weighted network (UWN) is constantly encountered in various big data-related applications. A UWN's topological information can be expressed by a Symmetric, High-dimensional and Incomplete (SHDI) matrix, upon which the representation learning task is essential for knowledge acquisition. However, existing models mostly fail in modeling its intrinsic symmetry or low-data density, resulting in the model's weak representation learning ability to its numerical features. For addressing this vital issue, this study presents a Proximal Symmetric Non-negative Latent-factor-analysis (PSNL) model with three-fold ideas: a) building a proximal term-incorporated, symmetry-aware, and data density-oriented learning objective subjected to the non-negativity constraints for ensuring its high representation learning ability;b) designing an Alternating Direction Method of Multipliers (ADMM)-based learning scheme for solving the learning objective on the premise of fast convergence;c) implementing self-adaptation of the model's multiple hyper-parameters via the Tree-structured of Parzen Estimators (TPE) algorithm, thus enabling its high scalability. Empirical studies on four UWNs from real applications demonstrate that the proposed PSNL model achieves higher representation accuracy than state-of-the-art models do, as well as promising computational efficiency.

关键词： Undirected Weighted Network Representation Learning Symmetric Non-negative Latent Factor Analysis Alternating Direction Method of Multipliers Tree-structured of Parzen Estimators Missing Data Estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-monitor System for Adaptive Image Saliency Detection Based on Attentive Mechanisms 4th

Multi-monitor System for Adaptive Image Saliency Detection B...

引用

4th International Conference on artificial intelligence in HCI (AI-HCI) Held as Part of the 25th International Conference on Human-Computer Interaction (HCII)

作者： Staffa, Mariacarla Barra, Paola Parthenope Univ Naples Sci & Techol Dept Naples Italy

ISBN: (纸本)9783031358937;9783031358944

One of the most powerful human-inspired cognitive processes adopted within robotics systems is visual attention to select salient information about the environment. The use of human-inspired cognitive processes has become an essential direction for the robotic research field, especially when robotics systems are deployed in complex and unstructured everyday environments where the limited computation capacity and the real-time requirements become the bottleneck of the system development. In the context above, developing a biologically plausible method must also meet the technical constraints needed to bridge the gap between bio-inspired influences and technical applicability. This paper proposes a bio-inspired visual attention system based on selective attention monitors to satisfy computational capacity constraints and identify semantically relevant information by prioritizing the visual stimuli based on both bottom-up and top-down information.

关键词： Multi-monitor system image salience detection attentive mechanisms

来源：评论

学校读者我要写书评

暂无评论

Uniform Substitution for Dynamic Logic with Communicating Hybrid Programs 1

引用

29th International Conference on Automated Deduction (CADE)

作者： Brieger, Marvin Mitsch, Stefan Platzer, Andre Ludwig Maximilians Univ Munchen Munich Germany Carnegie Mellon Univ Pittsburgh PA USA Karlsruhe Inst Technol Karlsruhe Germany

ISBN: (数字)9783031384998

ISBN: (纸本)9783031384998;9783031384981

This paper introduces a uniform substitution calculus for dL(CHP), the dynamic logic of communicating hybrid programs. Uniform substitution enables parsimonious prover kernels by using axioms instead of axiom schemata. Instantiations can be recovered from a single proof rule responsible for soundness-critical instantiation checks rather than being spread across axiom schemata in side conditions. Even though communication and parallelism reasoning are notorious for necessitating subtle soundness-critical side conditions, uniform substitution when generalized to dL(CHP) manages to limit and isolate their conceptual overhead. Since uniform substitution has proven to simplify the implementation of hybrid systems provers substantially, uniform substitution for dL(CHP) paves the way for a parsimonious implementation of theorem provers for hybrid systems with communication and parallelism.

关键词： Uniform substitution Parallel programs Differential dynamic logic Assumption-commitment reasoning CSP

来源：评论

学校读者我要写书评

暂无评论

Improved Spectral Norm Regularization for Neural Networks 20th

Improved Spectral Norm Regularization for Neural Networks

引用

20th International Conference on Modeling Decisions for artificial intelligence (MDAI)

作者： Johansson, Anton Engsner, Niklas Strannegard, Claes Mostad, Petter Chalmers Univ Technol Gothenburg Sweden Univ Gothenburg Dept Appl Informat Technol Gothenburg Sweden Volvo Grp Gothenburg Sweden

ISBN: (纸本)9783031334979;9783031334986

We improve on a line of research that seeks to regularize the spectral norm of the Jacobian of the input-output mapping for deep neural networks. While previous work rely on upper bounding techniques, we propose a scheme that targets the exact spectral norm. We evaluate this regularization method empirically with respect to its generalization performance and robustness. Our results demonstrate that this improved spectral regularization scheme outperforms L2-regularization as well as the previously used upper bounding technique. Moreover, our results suggest that exact spectral norm regularization and exact Frobenius norm regularization have comparable performance. We analyze these empirical findings in the light of the mathematical relations that hold between the spectral and the Frobenius norms. Lastly, in light of our evaluation we revisit an argument concerning the strong adversarial protection that Jacobian regularization provides and show that it can be misleading. In summary, we propose a new regularization method and contribute to the practical and theoretical understanding of when one regularization method should be preferred over another.

关键词： Deep learning Robustness Jacobian regularization

来源：评论

学校读者我要写书评

暂无评论

SpotGAN: A Reverse-Transformer GAN Generates Scaffold-Constrained Molecules with Property Optimization

SpotGAN: A Reverse-Transformer GAN Generates Scaffold-Constr...

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Li, Chen Yamanishi, Yoshihiro Nagoya Univ Grad Sch Informat Nagoya Aichi 4648602 Japan

ISBN: (纸本)9783031434112;9783031434129

Generating molecules with a given scaffold is a challenging task in drug-discovery. Scaffolds impose strict constraints on the generation of molecules. Moreover, the order of the simplified molecular-input line-entry system (SMILES) strings changes substantially during sequence expansion. This study presents a scaffold-constrained, property-optimized transformer GAN (SpotGAN) to solve these issues. SpotGAN employs a decoration generator that fills decorations into a given scaffold using a transformer-decoder variant. The discriminator is a transformer-encoder variant with a global receptive field that improves the realism of the generated molecules. The chemical properties are optimized through reinforcement learning (RL), affording molecules with high property scores. Additionally, an extension of SpotGAN, called SpotWGAN, is proposed to optimize and stabilize the training process leveraging the Wasserstein distance and mini-batch discrimination. Experimental results show the usefulness of the proposed model on scaffold-constrained molecular-generation tasks in terms of the drug-likeness, solubility, synthesizability, and bioactivity of the generated molecules(1 Our code is available at: https://***/naruto7283/SpotGAN).

关键词： Deep learning Molecular generation Scaffold-constrained

来源：评论

学校读者我要写书评

暂无评论

Fast Server Learning Rate Tuning for Coded Federated Dropout 1

引用

1st International Workshop on Trustworthy Federated Learning (FL)

作者： Verardo, Giacomo Barreira, Daniel Chiesa, Marco Kostic, Dejan Maguire, Gerald Q., Jr. KTH Royal Inst Technol Stockholm Sweden

ISBN: (数字)9783031289965

ISBN: (纸本)9783031289958;9783031289965

In Federated Learning (FL), clients with low computational power train a common machine model by exchanging parameters via updates instead of transmitting potentially private data. Federated Dropout (FD) is a technique that improves the communication efficiency of a FL session by selecting a subset of model parameters to be updated in each training round. However, compared to standard FL, FD produces considerably lower accuracy and faces a longer convergence time. In this chapter, we leverage coding theory to enhance FD by allowing different sub-models to be used at each client. We also show that by carefully tuning the server learning rate hyper-parameter, we can achieve higher training speed while also reaching up to the same final accuracy as the no dropout case. Evaluations on the EMNIST dataset show that our mechanism achieves 99.6% of the final accuracy of the no dropout case while requiring 2.43x less bandwidth to achieve this level of accuracy.

关键词： Federated Learning Hyper-parameters tuning Coding Theory

来源：评论

学校读者我要写书评

暂无评论

Online Unsupervised Anomaly Detection in Stream Data with Spiking Neural Networks Using Dynamic Scoring 1

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Li, Yaling Ge, Jintian Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China Univ Jinan Ind Sch Standardizat Jinan 250002 Peoples R China

ISBN: (数字)9789819947522

ISBN: (纸本)9789819947515;9789819947522

Unsupervised anomaly discovery in stream data is a challenging task, as it involves detecting unusual patterns in data that is constantly evolving over time. Online data-stream outlier detection can indeed be more difficult and challenging. This is because new data points are continuously arriving, and the outlier detection algorithm must process them in real-time. Our idea is to use online evolving spiking neural network classifier and dynamic outlier score normalization to determine whether the current data point is an outlier. The evolutionary algorithm helps the network adapt to changing patterns in the data over time, while the dynamic outlier score normalization adjusts the outlier score based on the distribution of data points over a moving window of time. Our approach is found superior in terms of effectiveness than the other solutions provided in the literature when applied to data streams from the Numenta Anomaly Benchmark repository.

关键词： Unsupervised anomaly detection Data stream Evolving Spiking Neural Networks Dynamic scoring

来源：评论

学校读者我要写书评

暂无评论

Quantum Circuit Compilation for the Graph Coloring Problem 1

引用

21st International Conference of the Italian-Association-for-artificial-intelligence (AIxIA)

作者： Oddi, Angelo Rasconi, Riccardo Baioletti, Marco Santucci, Vieri Giuliano Beck, Hamish Inst Cognit Sci & Technol ISTC CNR Rome Italy Univ Perugia Perugia Italy ESA European Space Res & Technol Ctr Adv Concepts Team Noordwijk Netherlands

ISBN: (数字)9783031271816

ISBN: (纸本)9783031271809;9783031271816

In this work we investigate the performance of greedy randomised search (GRS) techniques to the problem of compiling quantum circuits that solve instances of the Graph Coloring problem. Quantum computing uses quantum gates that manipulate multi-valued bits (qubits). A quantum circuit is composed of a number of qubits and a series of quantum gates that operate on those qubits, and whose execution realises a specific quantum algorithm. Current quantum computing technologies limit the qubit interaction distance allowing the execution of gates between adjacent qubits only. This has opened the way to the exploration of possible techniques aimed at guaranteeing nearest-neighbor (NN) compliance in any quantum circuit through the addition of a number of so-called swap gates between adjacent qubits. In addition, technological limitations (decoherence effect) impose that the overall duration (i.e., depth) of the quantum circuit realization be minimized. One core contribution of the paper is the application of an upgraded version of the greedy randomized search (GRS) technique originally introduced in the literature that synthesises NN-compliant quantum circuits realizations, starting from a set of benchmark instances of different size belonging to the Quantum Approximate Optimization Algorithm (QAOA) class tailored for the Graph Coloring problem. We propose a comparison between the presented method and the SABRE compiler, one of the best-performing compilation procedures present in Qiskit, an open-source SDK for quantum development, both from the CPU efficiency and from the solution quality standpoint.

关键词： Randomized search Quantum circuit compilation Planning Scheduling Optimization

来源：评论

学校读者我要写书评

暂无评论

Graph Convolution Collaborative Filtering with Dense Embeddings 15th

Graph Convolution Collaborative Filtering with Dense Embeddi...

引用

15th International Conference on Computational Collective intelligence (ICCCI)

作者： Trung-Nam Bui Huynh Anh-Tuc Tran Ngoc-Thao Nguyen Vietnam Natl Univ Ho Chi Minh City Univ Sci Fac Informat Technol Ho Chi Minh City Vietnam

ISBN: (纸本)9783031414558;9783031414565

Recommender systems have been a vital part of many e-commerce and online services. These systems support profound user personalization by mining the semantic interactions between users and items in the database, thereby increasing customer satisfaction and revenue. Furthermore, collaborative filtering research has significantly advanced in recent years with the compelling expressiveness of graph-based neural networks. In this paper, we introduce a novel collaborative filtering approach that represents users and items as graph embeddings and effectively exploits the knowledge from these embeddings. First, the feature vectors for users and items are refined with multiple embedding propagation layers. We then use many dense layers to get extra information as much as possible, main purpose is to support embedding vectors in the propagation process and allow our model to better learning of the user-item interaction, making a noticeable difference in performance from prior works. Finally, we combine them before mapping to a predicted score. The proposed method has been empirically proven superior to the baselines and competitive with modern approaches on public benchmarks.

关键词： Recommender system Graph convolutional network (GCN) Neural graph collaborative filtering (NGCF)

来源：评论

学校读者我要写书评

暂无评论

Emotional Internet of Behaviors: A QoE-QoS Adjustment Mechanism 4th

Emotional Internet of Behaviors: A QoE-QoS Adjustment Mechan...

引用

4th International Conference on artificial intelligence in HCI (AI-HCI) Held as Part of the 25th International Conference on Human-Computer Interaction (HCII)

作者： Alipour, Mina Moghaddam, Mahyar T. Vaidhyanathan, Karthik Kristensen, Tobias Asmussen, Nicolai Krogager Univ Southern Denmark DK-5230 Odense Denmark IIIT Hyderabad Hyderabad 500032 India

ISBN: (纸本)9783031358906;9783031358913

The Internet of Behaviors (IoB) approach supports developing socio-technical systems based on humans' goals, characteristics, behaviors, and emotions. This paper shows how emotions and behaviors could impact the quality of software systems. We propose interactive control loops that supervise application and architecture adaptations toward enhancing the system quality of service (QoS) and human quality of experience (QoE). Under the IoB conceptual model, we first show how historical and real emotions could be the source of the design and adaptation of socio-technical systems. We further use a Reinforcement Learning (RL)-based approach as a self-adaptation supervisor of user interfaces (UIs) to users' emotions. The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users' QoE. If the control system detects a drop in QoS in emotion-based adaptations or other functions, another level of adaptation reconfigures the architecture towards better quality. We used the emotional IoB approach to develop a mobile application as a recommender system in emergency evacuation training. The app takes users' facial emotions and positions as input and adapts its UI to impact users' target emotions and task completion. In addition to UI adaptation, the system supports architecture adaptations to decrease response time if required. The evaluation process confirms the efficiency of the RL in iterations, as well as compared to other possible UI adaptation techniques. The results also show that architecture adaptations positively impact the system performance and users' emotions and performance.

关键词： Internet of Behaviors Emotions Quality of Experience Quality of Service Software Architecture User Interface Adaptation

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 << < 458 459 460 461 462 463 464 465 466 467 > >>

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：