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
- 2,463 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
1,355 篇 管理学
- 1,256 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4901-4910 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：

RED CoMETS: An Ensemble Classifier for Symbolically Represented Multivariate Time Series 8th

RED CoMETS: An Ensemble Classifier for Symbolically Represen...

引用

8th International Workshop on Advanced Analytics and Learning on Temporal Data (AALTD) at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Bennett, Luca A. Abdallah, Zahraa S. Univ Bristol Sch Engn Math & Technol Bristol Avon England Awerian Cambridge England

ISBN: (纸本)9783031498954;9783031498961

Multivariate time series classification is a rapidly growing research field with practical applications in finance, healthcare, engineering, and more. The complexity of classifying multivariate time series data arises from its high dimensionality, temporal dependencies, and varying lengths. This paper introduces a novel ensemble classifier called RED CoMETS (Random Enhanced Co-eye for Multivariate Time Series), which addresses these challenges. RED CoMETS builds upon the success of Co-eye, an ensemble classifier specifically designed for symbolically represented univariate time series, and extends its capabilities to handle multivariate data. The performance of RED CoMETS is evaluated on benchmark datasets from the UCR archive, where it demonstrates competitive accuracy when compared to state-of-the-art techniques in multivariate settings. Notably, it achieves the highest reported accuracy in the literature for the 'HandMovementDirection' dataset. Moreover, the proposed method significantly reduces computation time compared to Co-eye, making it an efficient and effective choice for multivariate time series classification.

关键词： Time series classification Multivariate time series Co-eye Symbolic representation Ensemble classification

来源：评论

学校读者我要写书评

暂无评论

A Fully Decentralized Privacy-Enabled Federated Learning System 15th

A Fully Decentralized Privacy-Enabled Federated Learning Sys...

引用

15th International Conference on Computational Collective intelligence (ICCCI)

作者： Ferenczi, Andras Badica, Costin Univ Craiova Fac Automat Comp & Elect Craiova Romania

ISBN: (纸本)9783031414558;9783031414565

This paper looks into the field of blockchain-based federated learning, an area that's been studied a lot but is often too abstract for real-world use. Most solutions stay inside academic discussions, and there's a lack of practical, usable options. Our work introduces a new system that uses blockchain for federated learning in a straightforward, real-world way. Our system includes novel features such as an innovative anti-plagiarism mechanism and a unique consensus method for validating training results. We explain our methods, main results, and what our work could mean for the future in the paper. Our study could help make blockchain-based federated learning more useful by changing how data is shared and learned, all while keeping privacy and decentralization. This could drive more work into creating usable solutions in this field.

关键词： Federated Learning Privacy Decentralized Blockchain

来源：评论

学校读者我要写书评

暂无评论

PRACM: Predictive Rewards for Actor-Critic with Mixing Function in Multi-Agent Reinforcement Learning 16th

PRACM: Predictive Rewards for Actor-Critic with Mixing Funct...

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Yu, Sheng Liu, Bo Zhu, Wei Liu, Shuhong Natl Univ Def Technol Sch Informat & Commun Wuhan 430014 Peoples R China

ISBN: (纸本)9783031402913;9783031402920

Inspired by the centralised training with decentralised execution (CTDE) paradigm, the field of multi-agent reinforcement learning (MARL) has made significant progress in tackling cooperative problems with discrete action spaces. Nevertheless, many existing algorithms suffer from significant performance degradation when faced with large numbers of agents or more challenging tasks. Furthermore, some specific scenarios, such as cooperative environments with penalties, pose significant challenges to these algorithms, which often lack sufficient cooperative behavior to converge successfully. A new approach, called PRACM, based on the Actor-Critic framework is proposed in this study to address these issues. PRACM employs a monotonic mixing function to generate a global action value function, Qtot, which is used to compute the loss function for updating the critic network. To handle the discrete action space, PRACM uses Gumbel-Softmax. And to promote cooperation among agents and to adapt to cooperative environments with penalties, the predictive rewards is introduced. PRACM was evaluated against several baseline algorithms in "Cooperative Predator-Prey" and the challenging "SMAC" scenarios. The results of this study illustrate that PRACM scales well as the number of agents and task difficulty increase, and performs better in cooperative tasks with penalties, demonstrating its usefulness in promoting collaboration among agents.

关键词： Multi-agent reinforcement learning Discrete action Collaborative task Mixing function Predictive reward

来源：评论

学校读者我要写书评

暂无评论

Label Distribution Learning with Discriminative Instance Mapping 27th

Label Distribution Learning with Discriminative Instance Map...

引用

27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

作者： Zhang, Heng-Ru Bai, Run-Ting Tang, Wen-Tao Southwest Petr Univ Sch Comp Sci Chengdu Peoples R China

ISBN: (纸本)9783031333736;9783031333743

Label distribution learning (LDL) is an effective tool to tackle label ambiguity since it allows one instance to be associated with multiple labels in different degrees. Therefore, the more complex but informative label space makes it challenging to directly model the relationship between original features and label distributions. In this paper, an algorithm called Label Distribution Learning with Discriminative Instance Mapping (LDLDIM) is proposed to select a discriminative instance pool (DIP) to map the original features into a more discriminative space. First, we design a criterion that incorporates label information to quantify the discriminative power of each instance. Second, we select several instances with the highest discriminative ability to construct the DIP, and map the instances to the discriminative space through the DIP. By exploiting label information, this criterion enables the selected DIP to ensure that instances that are close (far away) in label space remain close (far away) in the discriminative space. Finally, multiple regressions for prediction are trained on the label distributions and the new features that are obtained by distance mapping with DIP. Experiments and comparisons on 16 datasets illustrate that our algorithm outperforms 6 state-of-the-art LDL methods in most cases.

关键词： Label distribution learning Instance mapping Discriminative ability

来源：评论

学校读者我要写书评

暂无评论

Deep Imbalanced Time-Series Forecasting via Local Discrepancy Density

Deep Imbalanced Time-Series Forecasting via Local Discrepanc...

引用

5th International Workshop on Learning with Imbalanced Domains - Theory and Applications / European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Park, Junwoo Lee, Jungsoo Cho, Youngin Shin, Woncheol Kim, Dongmin Choo, Jaegul Choi, Edward Korea Adv Inst Sci & Technol KAIST Kim Jaechul Grad Sch AI Daejeon South Korea

ISBN: (纸本)9783031434235;9783031434242

Time-series forecasting models often encounter abrupt changes in a given period of time which generally occur due to unexpected or unknown events. Despite their scarce occurrences in the training set (i.e., data imbalance), abrupt changes incur loss that significantly contributes to the total loss (i.e., heteroscedasticity). Therefore, they act as noisy training samples and prevent the model from learning generalizable patterns, namely the normal states. To resolve overfitting problem posed by heteroscedasticity and data imbalance, we propose a reweighting framework that down-weights the losses incurred by abrupt changes and up-weights those by normal states. For the reweighting framework, we first define a measurement termed Local Discrepancy (LD) which measures the degree of abruptness of a change in a given period of time. Since a training set is mostly composed of normal states, we then consider how frequently the temporal changes appear in the training set based on LD (i.e., estimated LD density). Our reweighting framework is applicable to existing time-series forecasting models regardless of the architectures. Through extensive experiments on 12 time-series forecasting models over eight datasets with various in-output sequence lengths, we demonstrate that applying our reweighting framework reduces MSE by 10.1% on average and by up to 18.6% in the state-of-the-art model.

关键词： Time-series forecasting Data imbalance Noisy samples

来源：评论

学校读者我要写书评

暂无评论

Distant Supervision Relation Extraction with Improved PCNN and Multi-level Attention 1

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Zou, Yang Wang, Qifei Wang, Zhen Zhou, Jian Zeng, Xiaoqin Hohai Univ Sch Comp & Informat Inst Intelligence Sci & Technol Nanjing 210098 Peoples R China

ISBN: (数字)9783031402838

ISBN: (纸本)9783031402821;9783031402838

In the research field of relation extraction, a large amount of labeled training data can be quickly obtained through distant supervision. However, distant supervision will be inevitably accompanied by the problem of wrong labelling, and the noisy data can substantially hurt the performance of relation extraction model. Previous studies mainly focus on de-noising by designing neural networks with intra-bag or inter-bag attention, but do not sufficiently take noise interference at different levels into account. Moreover, the conventional approach Piecewise Convolutional Neural Network (PCNN) encodes sentences based on an assumption that each segmented feature contributes equally to the relation, which is unreasonable. To alleviate these issues, we propose a distant supervision relation extraction model with Improved PCNN(I-PCNN) and multi-level attention. By incorporating word-level, sentence-level and bag-level attention into the model, it can effectively reduce the noisy data in a data set. Besides, it also enhances PCNN by augmenting self-attention, which can promote the encoding quality of sentences. Experiments conducted on New York Times (NYT) data set show that the proposed model evidently outperforms several baseline models in terms of the metrics Precision, Recall, AUC, and P@N.

关键词： relation extraction distant supervision I-PCNN multi-level attention

来源：评论

学校读者我要写书评

暂无评论

Translators as Information Seekers: Strategies and Novel Techniques 4th

Translators as Information Seekers: Strategies and Novel Tec...

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： Qian, Ming Wu, Huaqing Charles River Analyt Cambridge MA 02138 USA ATA Certified Translator Foshan Peoples R China

ISBN: (纸本)9783031358937;9783031358944

Translators search for information to resolve various types of uncertainties they face such as confirming the source of original texts, gaining proper understanding, and verifying whether the selected keywords are spelled correctly, commonly used, or matched properly between source and target languages. Under the constraints of tighter time schedules and stricter cost-effectiveness requirements imposed by the machine translation (MT) plus human post-editing (PE) business model, translators strive to achieve the goals of information seeking with enhanced efficiency and accuracy. This study investigates four information seeking strategies: (1) top-ranked results or featured snippets returned by large-scale web search engines;(2) abductive reasoning based on search result counts returned by large-scale web search engines;(3) direct answers provided by ChatGPT-a long-form question-answering conversational AI;(4) A novel conversational search engine (***) combining OpenAI's GPT language modeling technology and a large Internet search engine-Microsoft Bing. Human users should focus on forming effective human queries to develop an effective collaboration between human and large-scaleweb search engines, long-form question-answering conversational AI systems, and conversational search engine. While top-ranked search results and count-based abductive reasoning are effective strategies, emerging technologies such as long-form question-answering conversational AI and conversational search engine provide accurate and comprehensive answers to specific queries, and additional data and resources such as reference links and related questions.

关键词： Search Strategy Information Seeking ChatGPT Abductive Reasoning Human Heuristics Large Language Model Conversational AI Long-form Question-answering Human-centered AI Human-machine Teaming Human-machine Collaboration Search Engine Answer Engine Conversational Search Engine AI-chat

来源：评论

学校读者我要写书评

暂无评论

Goal-Oriented Coordination with Cumulative Goals 24th

Goal-Oriented Coordination with Cumulative Goals

引用

24th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA)

作者： Ghose, Aditya Dam, Hoa Tomura, Shunichiro Philp, Dean Consoli, Angela Univ Wollongong Decis Syst Lab Wollongong NSW 2500 Australia Def Sci & Technol Grp Edinburgh SA 5111 Australia

ISBN: (纸本)9783031212024;9783031212031

Multi-actor coordination is in general a complex problem, with inefficient and brittle solutions. This paper addresses the problem of abstract coordination of multiple actors at the goal-level, which often enables us to avoid these problems. Goals in multi-actor settings often rely on the cumulative efforts of a group of distinct actors whose individual, measurable contributions accumulate to lead to the fulfillment of the goal. We formalize these as cumulative goals in a mathematical framework that permits us to measure individual actor contributions on a variety of scales (including qualitative ones). We view these as softgoals, a conception general enough to incorporate the more traditional hardgoals. Within this mathematical setting, we address the coordination problem as one of deciding which actor is allocated to fulfilling each goal of interest (and the associated problem of goal model maintenance). We also report some empirical evaluation results.

关键词： Coordination reactions

来源：评论

学校读者我要写书评

暂无评论

Overfitting Problem in the Approximate Bayesian Computation Method Based on Maxima Weighted Isolation Kernel

Overfitting Problem in the Approximate Bayesian Computation ...

引用

14th International Symposium on artificial intelligence (ISAI)

作者： Nagornov, Iurii S. Natl Inst Adv Ind Sci & Technol 2-4-7 AomiKoto Ku Tokyo 1350064 Japan

ISBN: (纸本)9783031291678;9783031291685

A branching processes model yields an unevenly stochastically distributed dataset that consists of highly sparse and highly dense regions. This work addresses the problem of precisely evaluating parameters for such a model. An approximate Bayesian computation method is developed that is based on Isolation Kernel mapping with additional parameter generation and selection processes, i.e. meta-sampling. The method involves the transformation of row data to a Hilbert space and the measurement of the similarity between generated parameters and maxima weighted Isolation Kernel mapping related to the observation point. Meta-sampling algorithm requires no gradient calculation and is dimension independent. This work is devoted to the problem of the fitting and overfitting of the hyperparameters for the method such as a number of Voronoi sites and a number of trees of isolation forest. Here, we discuss the reasons for overfitting and how to fit parameters properly. The advantages of the proposed meta-sampling method are illustrated using multidimensional test data as well as a specific example focused on cancer cell evolution.

关键词： Isolation Kernel Overfitting Problem Approximate Bayesian Computation Maxima Weighted Isolation Kernel Mapping Branching Processes

来源：评论

学校读者我要写书评

暂无评论

Graph Strategy for Interpretable Visual Question Answering 15th

Graph Strategy for Interpretable Visual Question Answering

引用

15th International Conference on artificial General intelligence (AGI)

作者： Sarkisyan, Christina Savelov, Mikhail Kovalev, Alexey K. Panov, Aleksandr I. Moscow Inst Phys & Technol Dolgoprudnyi Russia AIRI Moscow Russia Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia

ISBN: (纸本)9783031199066;9783031199073;9783031199066

In the paper, we consider the task of Visual Question Answering, an important task for creating General artificial intelligence (AI) systems. We propose an interpretable model called GS-VQA. The main idea behind it is that a complex compositional question could be decomposed into a sequence of simple questions about objects' properties and their relations. We use the Unified estimator to answer questions from that sequence and test the proposed model on CLEVR and THORVQA datasets. The GS-VQA model demonstrates results comparable to the state of the art while maintaining transparency and interpretability of the response generation process.

关键词： Interpretable visual question answering Graph explanations Unified estimator

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 << < 487 488 489 490 491 492 493 494 495 496 > >>

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：