检索结果-内蒙古大学图书馆

Research Progress of Parallel control and management

IEEE/CAA Journal of Automatica Sinica 2020年第2期7卷 355-367页

作者： Gang Xiong Xisong Dong Hao Lu Dayong Shen State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China College of Systems Engineering National University of Defense TechnologyChangsha 410073China

Based on ACP(artificial systems,computational experiments,and parallel execution)methodology,parallel control and management has become a popularly systematic and complete solution for the control and management of complex *** paper focuses on summarizing comprehensive review of the research literature of parallel control and management achieved in the recent years including the theoretical framework,core technologies,and the application *** future research,application directions,and suggestions are also discussed.

关键词： ACP methodology artificial systems computational experiments parallel control parallel management parallel systems

来源：评论

学校读者我要写书评

暂无评论

Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Yuanyang Wang, Zhi Zhu, Yuanheng Chen, Chunlin Zhao, Dongbin The Department of Control Science and Intelligent Engineering School of Management and Engineering Nanjing University Nanjing210093 China The Research Center for Novel Technology of Intelligent Equipment Nanjing University Nanjing210093 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without considering the inherent ordering between the discrete atomic actions, the explosion in the number of discrete actions can possess undesired properties and induce a higher variance for the policy gradient estimator. In this paper, we introduce a straightforward architecture that addresses this issue by constraining the discrete policy to be unimodal using Poisson probability distributions. This unimodal architecture can better leverage the continuity in the underlying continuous action space using explicit unimodal probability distributions. We conduct extensive experiments to show that the discrete policy with the unimodal probability distribution provides significantly faster convergence and higher performance for on-policy reinforcement learning algorithms in challenging control tasks, especially in highly complex tasks such as Humanoid. We provide theoretical analysis on the variance of the policy gradient estimator, which suggests that our attentively designed unimodal discrete policy can retain a lower variance and yield a stable learning process. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Geometry Problem Solving Based on Counter-Factual Evolutionary Reasoning 19

Geometry Problem Solving Based on Counter-Factual Evolutiona...

引用

19th IEEE International Conference on Automation Science and Engineering, CASE 2023

作者： Song, Bing Xiong, Gang Shen, Zhen Zhu, Fenghua Lv, Yisheng Ye, Peijun Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Management and Control for Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences The Beijing Engineering Research Center of Intelligent Systems and Technology China Chinese Academy of Sciences The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Dongguan523808 China Qingdao Academy of Intelligent Industries Intelligent Manufacturing Center Qingdao266000 China

ISBN: (纸本)9798350320695

As a representative topic in natural language processing and automated theorem proving, geometry problem solving requires an abstract problem understanding and symbolic reasoning. A major challenge here is to find a feasible reasoning sequence that is consistent with given axioms and the theorems already proved. Most recent methods have exploited neural network-based techniques to automatically discover eligible solving steps. Such a kind of methods, however, is greatly impacted by the expert solutions for training. To improve the accuracy, this paper proposes a new method called counterfactual evolutionary reasoning, which uses a generative adversarial network to generate initial reasoning sequences and then introduces counterfactual reasoning to explore potential solutions. By directly exploring theorem candidates rather than the neural network selection, the new method can sufficiently extend the searching space to get a more appropriate reasoning step. Through comparative experiments on the recent proposed Geometry3k, the largest geometry problem solving dataset, our method generally achieves a higher accuracy than most previous methods, bringing an overall improvement about 4.4% compared with the transformer models. © 2023 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Parallel Theaters in CPSS: From Shadows of ISDOS to Intelligence of Decision Theaters

引用

IEEE/CAA Journal of Automatica Sinica 2025年第6期12卷 1059-1062页

作者： Qinghua Ni Buday Viktória Fei Lin Jun Huang Levente Kovács Nan Zheng Fei-Yue Wang Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology Macau China Innovation Management Doctoral School Obuda University Budapest Hungary John von Neumann Faculty of Informatics Obuda University Budapest Hungary State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China DeSci Center of Parallel Intelligence and the University Research and Innovation Center at Obuda University State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

As Artificial Intelligence (AI) is moving fast from Large Language Models (LLMs) to AI Agents and Agentic Intelligence, the need to incorporate new AI into Decision Intelligence (DI) is becoming more and more urgent for both practical and theoretic reasons: both decision and process complexities would be significantly increased due to the use of advanced AI tools and agents, and both traditional and recent thinking must be rethought and reconstructed accordingly. Our perspective would like to address this important issue based on some historical milestone developments in Computer-Aided Software Engineering (CASE) and recent efforts in digital theatrical technology [1].

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simplified Variant for Graph Convolutional Network Based Knowledge Graph Completion Model 8

A Simplified Variant for Graph Convolutional Network Based K...

引用

8th International Conference on Data Science in Cyberspace, DSC 2023

作者： Wang, Yashen Li, Qiang Zhang, Yi Zhang, Xuecheng Ju, Zhuoya Sun, Jian Beijing China Scientific and Technological Innovation Center of Ari Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China Cetc Academy of Electronics and Information Technology Group Co. Ltd. Beijing China Khoury College of Computer Science Northeastern University United States Scientific and Technological Innovation Center of Ari Beijing China Qi An Xin Technology Group Inc. Beijing China

ISBN: (纸本)9798350331035

Knowledge graphs (KGs) serve as useful resources for various applications including machine learning, data mining, and artificial intelligence. Knowledge Graph Completion (KGC) aims at reasoning over known (observed) facts and infer the missing (unobserved) relationships, to improve KG's coverage. Many recent works have laid stress on leveraging Graph Convolutional Networks (GCNs) for KGC task, which obtain good representation learning ability for graph-structured data, and have achieved satisfactory results. However, GCN-based researches continue to improve these lines of models by introducing an increasingly complex feature space. Especially, the hyper-parameter space of conventional GCN-based KGC model is too huge, resulting in low computational efficiency and excessive storage pressure. To overcome this problem, this paper investigates a simplified and generic variant for GCN-based KGC model, and shows that simple changes in the architecture of the underlying architecture (with a Subtraction Operator and an Addition Operator), can compte with state-of-the-art GCN-based models. Therefore, this paper proposes a easy-to-accomplish plug-in unit, which could be loaded into any current GCN-based KGC architectures, and help them maximize the maintenance of native model's original performance while significantly reducing parameter scale. © 2023 IEEE.

关键词： Graph Convolutional Network Knowledge Graph Knowledge Graph Completion Representation Learning

来源：评论

学校读者我要写书评

暂无评论

Learning Representation with Q-irrelevance Abstraction for Reinforcement Learning 11

Learning Representation with Q-irrelevance Abstraction for R...

引用

11th International Conference on Intelligent control and Information Processing, ICICIP 2021

作者： Hao, Shuai Li, Luntong Liu, Minsong Zhu, Yuanheng Zhao, Dongbin Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing China School of Software Beihang University Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665425155

In order to improve the performance of deep reinforcement learning (DRL) algorithm in high-dimensional observation environments, we propose a new auxiliary task to learn representations to aggregate task-relevant information of observations. Inspired by Q-irrelevance abstraction, our auxiliary task trains a deep Q-network (DQN) to predict the true Q value distribution over all discrete actions. Then we use the output of DQN to train the encoder to discriminate states with different Q values. The encoder is used as the representation of proximal policy optimization (PPO). The resulting algorithm is called as Q-irrelevance Abstraction for Reinforcement Learning (QIARL). After training, the encoder can aggregate states with similar Q value distributions together for any policy and any action. Thus the encoder can encode the important information that is relevant to reinforcement learning task. We test QIARL in four Procgen environments compare with PPO, A2C and Rainbow. The experimental results show QIARL outperforms the other three algorithms. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stream Model for Human Motor Characteristics Learning

A Novel Two-Stream Model for Human Motor Characteristics Lea...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Xiang, Tian-Yu Zhou, Xiao-Hu Xie, Xiao-Liang Liu, Shi-Qi Yang, Hong-Jun Feng, Zhen-Qiu Hao, Jian-Long Hou, Zeng-Guang Institute of Automation The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The School of Information Shanxi University of Finance and Economics Taiyuan030006 China The CAS Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China Institute of Systems Engineering Macau University of Science and Technology The Joint Laboratory of Intelligence Science and Technology Taipa China

ISBN: (纸本)9781665481090

Electroencephalogram (EEG) is one of the most pop-ular sources for learning human motor characteristics. However, most current methods only consider its temporal features and overlook spatial information. This paper proposes a novel two-stream model based on spatial and temporal features to learn human motor characteristics from EEG signals. The spatial stream is analyzed by graph neural networks (GNN) to extract the relationship among different channels. Adjacent matrices can be learned through the training process, unlike pre-defined ones used in other GNN-based EEG analysis methods. The temporal stream is processed with mixed convolution structures, which consist ID convolution, depthwise convolution, and separable convolution. The features of two streams are fused with fully-connected neural networks for human motor characteristics learning. Experimental results show the proposed model can achieve the accuracy of 0.684/0.709 (four classes motor imagery) in subject-independent/dependent schemes, demonstrating the promising for it used in brain computer interface (BCI) scenarios. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PiAGI: The Concept, Mechanism and Framework

PiAGI: The Concept, Mechanism and Framework

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Qiang Li Zhuoya Ju Lili Fan Xin Liu Wenhua Liu Feiyue Wang Scientific and Technological Innovation Center Beijing China The School of Automation Beijing Institute of Technology Beijing China School of Big Data & Cyber Security China University of Petroleum Qingdao China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

As social production and living spaces gradually expand from the physical and information domains to the cognitive and social domains, this article addresses the new changes brought about by these expansions. Starting from the new impact of era of intelligent connectivity on social cognitive management, it analyzes the urgent need to enhance social cognitive management capabilities centered on cognitive decision-making, identifying the core key as Adversarial Generated Intelligence (AGI). It delves into the conceptual characteristics, operating mechanisms, and winning strategies of AGI, identifies the new challenges it faces, and proposes a Parallel Intelligence empowering AGI (PiAGI) system architecture through the empowerment of parallel intelligence. This provides theoretical support for improving social cognitive management capabilities centered on cognitive decision-making.

关键词： Decision making systems architecture Production Digital twins Faces

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

来源：评论

学校读者我要写书评

暂无评论

TASF: Terrestrial-Aerial Synergistic Framework for a New Generation of Intelligent Transportation

TASF: Terrestrial-Aerial Synergistic Framework for a New Gen...

引用

International Conference on Intelligent Transportation

作者： Cong Wang Dujun Nie Ruijun Zhang Siyu Teng Long Chen State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Hong Kong Baptist University Kowloon Hong Kong China WAYTOUS Inc. Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems and the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Terrestrial-Aerial Synergistic Framework (TASF) represents a novel approach to intelligent transportation, integrating terrestrial and aerial vehicles to enhance urban transportation efficiency and capacity. In this paper, we offer an in-depth analysis of TASF, emphasizing its innovative applications in urban transportation, parcel delivery, and emergency response services. TASF incorporates a five-layer architecture comprising perception, communication, planning, control, and interaction. With the five-layer architecture, TASF can achieve effective collaboration among terrestrial and aerial vehicles, encompassing two principal features: terrestrial-aerial synergistic parallel perception and multi-agent parallel management. Parallel perception results from fusing Bird's Eye View (BEV) representations from Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs), whereas decentralized multi-agent management employs foundational models to enhance decision-making capabilities. Additionally, we consider challenges and potential solutions related to TASF, including safety, reliability, energy efficiency, management and integration. TASF marks a paradigm-shifting leap in the realm of intelligent transportation systems, providing a scalable and efficacious solution tailored to the dynamic requirements of urban mobility and emergency services.

关键词： Foundation models Urban areas Decision making Transportation Emergency services Land vehicles Energy efficiency Planning Reliability Vehicle dynamics

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：