检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Zhao, Wenshuai Zhao, Yi Li, Zhiyuan Kannala, Juho Pajarinen, Joni Department of Electrical Engineering and Automation Aalto University Finland School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Computer Science Aalto University Finland University of Oulu Finland

Relative overgeneralization (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behaviors of other *** methods have been proposed for addressing RO in multi-agent policy gradient (MAPG) methods although these methods produce state-of-the-art *** address this gap, we propose a general, yet simple, framework to enable optimistic updates in MAPG methods that alleviate the RO *** approach involves clipping the advantage to eliminate negative values, thereby facilitating optimistic updates in *** optimism prevents individual agents from quickly converging to a local ***, we provide a formal analysis to show that the proposed method retains optimality at a fixed *** extensive evaluations on a diverse set of tasks including the Multi-agent MuJoCo and Overcooked benchmarks, our method outperforms strong baselines on 13 out of 19 tested tasks and matches the performance on the rest. Copyright 2024 by the author(s)

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Overview of Finite/Fixed-Time control and Its Application in engineering Systems

引用

IEEE/CAA Journal of Automatica Sinica 2022年第12期9卷 2106-2120页

作者： Yang Liu Hongyi Li Zongyu Zuo Xiaodi Li Renquan Lu IEEE College of Automation and Electronics Engineering Qingdao University of Science and TechnologyQingdao 266061 School of Automation Guangdong University of TechnologyGuangzhou 510006China School of Automation Guangdong University of Technologyand also with the Guangdong Province Key Laboratory of Intelligent Decision and Cooperative ControlGuangzhou 510006China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100083China School of Mathematics and Statistics Shandong Normal UniversityBeijing 100083China Center for Control and Engineering Computation Shandong Normal UniversityJinan 250014China

The finite/fixed-time stabilization and tracking control is currently a hot field in various systems since the faster convergence can be obtained. By contrast to the asymptotic stability,the finite-time stability possesses the better control performance and disturbance rejection property. Different from the finite-time stability, the fixed-time stability has a faster convergence speed and the upper bound of the settling time can be estimated. Moreover, the convergent time does not rely on the initial *** work aims at presenting an overview of the finite/fixed-time stabilization and tracking control and its applications in engineering systems. Firstly, several fundamental definitions on the finite/fixed-time stability are recalled. Then, the research results on the finite/fixed-time stabilization and tracking control are reviewed in detail and categorized via diverse input signal structures and engineering applications. Finally, some challenging problems needed to be solved are presented.

关键词： Adding a power integrator finite/fixed-time control and application homogeneous theory sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Annotated survey and perspectives on rail transport energy system RAMS evaluation technology

引用

Green Energy and Intelligent Transportation 2024年第3期3卷 75-90页

作者： Ruifeng Shi Lingzhi Zhang Feng Lin Jin Ning Limin Jia Kwang Y.Lee School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China China Institute of Energy and Transportation Integrated Development Beijing 102206China State Key Lab of Rail Traffic Control&Safety Beijing Jiaotong UniversityBeijing 100044China Department of Electrical and Computer Engineering Baylor UniversityWacoTX 76798USA

The rail transit system plays a crucial role in modern *** the increasing demand for clean and green energy in the transport sector,its energy system is expected to achieve low-carbon and highly efficient energy utilization in rail ***,the gradual development of the rail transport energy system has led to an increase in its complexity,and the rising difficulty of system assessment has faced the limitations of traditional assessment ***,it is essential to develop effective assessment *** paper begins by providing a systematic review of the development status of Reliability,Availability,Maintainability and Safety(RAMS)assessment and analyzing the shortcomings of traditional RAMS assessment technology in the context of rail transit energy ***,based on the four fundamental properties of RAMS,it summarizes the current state of key assessment technologies in the field of rail ***,the paper delves into the challenges and potential solutions concerning the implementation of RAMS assessment technology for rail transit energy ***,the paper offers an outlook on the future development of RAMS assessment for rail transport energy *** comprehensively analyzing these aspects,the paper aims to contribute valuable insights into optimizing the rail transit energy system,promoting its sustainable and efficient operation in the context of clean and green energy utilization.

关键词： Integration of energy and transportation RAMS evaluation Rail transit energy system

来源：评论

学校读者我要写书评

暂无评论

CAPACITY ALLOCATION METHOD OF BATTERY ENERGY STORAGE SYSTEM CONSIDERING MULTI-SERVICE TARGET LEVEL ASSESSMENT

引用

International Journal of electrical engineering 2022年第5期29卷 141-153页

作者： Ma, Suliang Wu, Yiwen Jiang, Yuan Li, Yaxin Li, Jianlin School of Electrical and Control Engineering North China University of Technology Shijingshan District Beijing China Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Haidian District Beijing China

Rational planning of battery energy storage system is the key technology to solve the problem of high proportion of new energy consumption and the requirements of high performance power supply. Starting from the multiple application dimensions of power supply, power grid, load and battery energy storage system, this paper proposes a method of battery energy storage system capacity allocation based on multi-objective comprehensive evaluation. Firstly, the capacity configuration model of battery energy storage system is established from two aspects of service objectives and operation constraints;Then, under the two-level optimization framework, the capacity allocation scheme of the battery energy storage system is formed by using particle swarm optimization and multi- attribute decision-making methods;Finally, the configuration results of IEEE33 nodes with high proportion of distributed new energy access are analyzed, and the influence of model parameters and target orientation on the capacity of battery energy storage system is discussed. The simulation results show that the proposed method can flexibly and effectively configure the battery energy storage system, complete multiple different target service requirements, and promote the scientific application of the battery energy storage system. © 2022, Chinese Institute of electrical engineering. All rights reserved.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Toward quantum unmanned systems

引用

Science China(Technological Sciences) 2024年第7期67卷 2277-2280页

作者： CHENG ShuMing QI HongSheng SUN Yue LIU LiJun XIE ShaoRong REN XiaoQiang Department of Control Science and Engineering Tongji UniversityShanghai 200092China Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China Cipher Cloud Core Ltd. Beijing 100085China College of Mathematics and Computer Science Shanxi Normal UniversityLinfen 041081China School of Computer Engineering and Science Shanghai UniversityShanghai 200444China School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444China

1 Quantum information technology Quantum information technology utilizes physical systems at the microscopic level, such as photon, atom, ion, and superconducting, to accomplish information-processing tasks that are impossible for the classical macroscopic world. During the past decade, significant process has been achieved in the pursuit of quantum technology into practical applications,generating great research interest from various domains, with the potential to radically change our information infrastructure [1–3].

关键词： quantum utilize generating

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode control for Recurrent Neural Networks With Time-Varying Delays and Impulsive Effects

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1319-1321页

作者： Lanfeng Hua Kaibo Shi Zheng-Guang Wu Soohee Han Shouming Zhong the School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China the School of Electronic Information and Electrical Engineering Chengdu UniversityChengdu 610106China the Institute of Cyber-Systems and Control Zhejiang UniversityHangzhou 310027China the Department of Electrical Engineering and Convergence IT Engineering Pohang University of Science and TechnologyPohang 37673South Korea the School of Mathematics Sciences University of Electronic Science and Technology of ChinaChengdu 611731China

Dear Editor,This letter studies the problem of sliding mode control(SMC)design for recurrent neural networks(RNNs)with impulsive disturbances and time-varying transmission *** this end,an appropriate integral sliding ... 详细信息

关键词： impulsive letter delays

来源：评论

学校读者我要写书评

暂无评论

Efficient Prompting for LLM-Based Generative Internet of Things

引用

IEEE Internet of Things Journal 2025年第1期12卷 778-791页

作者： Xiao, Bin Kantarci, Burak Kang, Jiawen Niyato, Dusit Guizani, Mohsen University of Ottawa School of Electrical Engineering and Computer Science OttawaONK1N 6N5 Canada Guangdong University of Technology School of Automation Guangzhou510006 China Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore Singapore Mohamed bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

Large language models (LLMs) have demonstrated remarkable capacities on various tasks, and integrating the capacities of LLMs into the Internet of Things (IoT) applications has drawn much research attention recently. Due to security concerns, many institutions avoid accessing state-of-the-art commercial LLM services, requiring the deployment and utilization of open-source LLMs in a local network setting. However, open-source LLMs usually have more limitations regarding their performance, such as their arithmetic calculation and reasoning capacities, and practical systems of applying LLMs to IoT have yet to be well-explored. Therefore, we propose an LLM-based Generative IoT (GIoT) system deployed in the local network setting in this study. To alleviate the limitations of LLMs and provide service with competitive performance, we apply prompt engineering methods to enhance the capacities of the open-source LLMs, design a Prompt Management Module and a Postprocessing Module to manage the tailored prompts for different tasks and process the results generated by the LLMs. To demonstrate the effectiveness of the proposed system, we discuss a challenging table question answering (Table-QA) task as a case study of the proposed system, as tabular data is usually more challenging than plaintext because of their complex structures, heterogeneous data types and sometimes huge sizes. We conduct comprehensive experiments on the two popular Table-QA data sets, and the results show that our proposal can achieve competitive performance compared with state-of-the-art LLMs, demonstrating that the proposed LLM-based GIoT system can provide competitive performance with tailored prompting methods and is easily extensible to new tasks without training. © 2014 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1614-1625页

作者： Sun, Genchen Liu, Zhengkun Gan, Lin Su, Hang Li, Ting Zhao, Wenfeng Sun, Biao Tianjin University School of Electrical and Information Engineering Tianjin300072 China Northwestern Polytechnical University School of Automation Xi'an710072 China Politecnico di Milano Department of Electronics Information and Bioengineering Milan20133 Italy Chinese Academy of Medical Science Institute of Biomedical Engineering Pecking Union Medical College Tianjin300020 China Binghamton University Department of Electrical and Computer Engineering State University of New York BinghamtonNY United States

In recent years, Neural Architecture Search (NAS) has marked significant advancements, yet its efficacy is marred by the dependence on substantial computational resources. To mitigate this, the development of NAS benchmarks has emerged, offering datasets that enumerate all potential network architectures and their performances within a predefined search space. Nonetheless, these benchmarks predominantly focus on convolutional architectures, which are criticized for their limited interpretability and suboptimal hardware efficiency. Recognizing the untapped potential of Spiking Neural Networks (SNNs) - often hailed as the third generation of neural networks for their biological realism and computational thrift - this study introduces SpikeNAS-Bench. As a pioneering benchmark for SNN, SpikeNAS-Bench utilizes a cell-based search space, integrating leaky integrate-and-fire (LIF) neurons with variable thresholds as candidate operations. It encompasses 15,625 candidate architectures, rigorously evaluated on CIFAR10, CIFAR100 and Tiny-ImageNet datasets. This paper delves into the architectural nuances of SpikeNAS-Bench, leveraging various criteria to underscore the benchmark's utility and presenting insights that could steer future NAS algorithm designs. Moreover, we assess the benchmark's consistency through three distinct proxy types: zero-cost-based, early-stop-based, and predictor-based proxies. Additionally, the paper benchmarks seven contemporary NAS algorithms to attest to SpikeNAS-Bench's broad applicability. We commit to providing training logs, diagnostic data for all candidate architectures, and the promise to release all code and datasets post-acceptance, aiming to catalyze further exploration and innovation within the SNN domain. SpikeNAS-Bench is open source at https://***/XXX (hidden for double anonymous review). © 2020 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

ℋ₂ state-feedback control for continuous semi-Markov jump linear systems with rational transition rates

引用

International Journal of control 2023年第1期96卷 1-11页

作者： de Almeida, M. Souza, M. Fioravanti, A.R. Costa, O.L.V. School of Mechanical Engineering University of Campinas Campinas Brazil School of Electrical and Computer Engineering University of Campinas Campinas Brazil Department of Telecommunications and Control Engineering Polytechnic School University of Sao Paulo Sao Paulo Brazil

This paper presents the (Formula presented.) State-Feedback control for Continuous Semi-Markov Jump Linear Systems where the transition rates are given by the ratio of polynomials of the sojourn time. We show that, for instance, Rayleigh-, Erlang- and a class of Weibull-distributed sojourn time can be described by such a model. We present general results on the stability and on the (Formula presented.) of Semi-Markov Jump Linear Systems and provide sum-of-squares conditions for norm calculation and state-feedback control design problems. We conclude the paper by presenting two numerical examples that point out the main features of our results and by discussing future directions and related problems. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

关键词： convex optimisation Linear systems stochastic systems sum-of-squares

来源：评论

学校读者我要写书评

暂无评论

A BP neural network time delay prediction method based on phase space reconstruction 8

A BP neural network time delay prediction method based on ph...

引用

8th International Conference on Electronic Technology and Information Science, ICETIS 2023

作者： Sun, Wenzhe Zhang, Liyan Xu, Huigang Dou, Shunkun Li, Changxian School of automation and electrical engineering Dalian Jiaotong University Dalian116028 China School of computer and communication engineering Dalian Jiaotong University Dalian116028 China

ISBN: (纸本)9781510666535

In this paper, a neural network time delay prediction method based on phase space reconstruction is presented. This method reconstructs one-dimensional chaotic time series in phase space according to the internal law through phase space reconstruction, and uses BP neural network algorithm to predict the time delay. Simulation experiments show that this method has good prediction performance. © 2023 SPIE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：