检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Kun Shao Yuanheng Zhu Zhentao Tang Dongbin Zhao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In partially observable fully cooperative games, agents generally tend to maximize global rewards with joint actions, so it is difficult for each agent to deduce their own contribution. To address this credit assignment problem, we propose a multi-agent reinforcement learning algorithm with counterfactual reward mechanism, which is termed as CoRe algorithm. CoRe computes the global reward difference in condition that the agent does not take its actual action but takes other actions, while other agents fix their actual actions. This approach can determine each agent's contribution for the global reward. We evaluate CoRe in a simplified Pig Chase game with a decentralised Deep Q Network (DQN) framework. The proposed method helps agents learn end-to-end collaborative behaviors. Compared with other DQN variants with global reward, CoRe significantly improves learning efficiency and achieves better results. In addition, CoRe shows excellent performances in various size game environments.

关键词： Games Learning (artificial intelligence) Machine learning Collaboration Training Task analysis Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Shift-Invariant Convolutional Network Search

Shift-Invariant Convolutional Network Search

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Nannan Li Yaran Chen Zixiang Ding Dongbin Zhao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of artificial intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

The development of Neural Architecture Search (NAS) makes Convolutional Neural Networks (CNN) more diverse and effective. But previous NAS approaches don't pay attention to the shift-invariant of CNN. Without the shift-invariant, convolutional network is not robust enough when input data is disturbed or damaged. Besides, taking accuracy as the only optimization goal of NAS cannot meet the increasingly diverse needs. In this paper, we propose Shift-Invariant Convolutional Network Search (SICNS). It uses one-shot NAS to search for shift-invariant convolutional network by incorporating the low-pass filter into the one-shot model. Furthermore, SICNS optimizes multiple indicators simultaneously through the multi-objective evolutionary algorithm. Through training one-shot model and evolving the architecture, we obtain convolutional networks which are robust and powerful on image classification task. Especially, our work can achieve 4.52% test error on CIFAR-10 with 0.7M parameters. And in case the input data are disturbed, the accuracy of searched network is 2.96% higher than network without low-pass filter.

关键词： Training Optimization Kernel Convolution Adaptation models Task analysis Search problems

来源：评论

学校读者我要写书评

暂无评论

ABCP: Automatic block-wise and channel-wise network pruning via joint search

arXiv

引用

arXiv 2021年

作者： Li, Jiaqi Li, Haoran Chen, Yaran Ding, Zixiang Li, Nannan Ma, Mingjun Duan, Zicheng Zhao, Dongbing The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China The University of Chinese Academy of Sciences Beijing China The College of Engineering and Computer Science Australian National University ACT2601 Australia

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rule-based network pruning methods can not reach a sufficient compression ratio with low accuracy loss and are time-consuming as well as laborious. In this paper, we propose Automatic Block-wise and Channel-wise Network Pruning (ABCP1) to jointly search the block-wise and channel-wise pruning action with deep reinforcement learning. A joint sample algorithm is proposed to simultaneously generate the pruning choice of each residual block and the channel pruning ratio of each convolutional layer from the discrete and continuous search space respectively. The best pruning action taking both the accuracy and the complexity of the model into account is obtained finally. Compared with the traditional rule-based pruning method, this pipeline saves human labor and achieves a higher compression ratio with lower accuracy loss. Tested on the mobile robot detection dataset, the pruned YOLOv3 model saves 99.5% FLOPs, reduces 99.5% parameters, and achieves 37.3× speed up with only 2.8% mAP loss. The results of the transfer task on the sim2real detection dataset also show that our pruned model has much better robustness performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The Combination of Two control Strategies for Series Hybrid Electric Vehicles

引用

IEEE/CAA Journal of Automatica Sinica 2019年第2期6卷 596-608页

作者： Can Luo Zhen Shen Simos Evangelou Gang Xiong Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Cloud Computing Center Chinese Academy of Sciences IEEE Department of Electrical and Electronic Engineering Imperial College London Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Qingdao Academy of Intelligent Industries

With most countries paying attention to the environment protection, hybrid electric vehicles have become a focus of automobile research and development due to the characteristics of energy saving and low emission. Power follower control strategy(PFCS) and DC-link voltage control strategy are two sorts of control strategies for series hybrid electric vehicles(HEVs). Combining those two control strategies is a new idea for control strategy of series hybrid electric vehicles. By tuning essential parameters which are the defined constants under DClink voltage control and under PFCS, the points of minimum mass of equivalent fuel consumption(EFC) corresponding to a series of variables are marked for worldwide harmonized light vehicles test procedure(WLTP). The fuel economy of series HEVs with the combination control schemes performs better compared with individual control scheme. The results show the effects of the combination control schemes for series HEVs driving in an urban environment.

关键词： DC-Link voltage control power follower control strategy series hybrid electric vehicles tuning

来源：评论

学校读者我要写书评

暂无评论

Social Manufacturing Pattern in the Intelligent Reform of the Shoes and Clothing Industry

Social Manufacturing Pattern in the Intelligent Reform of th...

引用

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

作者： Yansong Cao Yutong Wang Juwu Dai Xihao Zhu Fei-Yue Wang Macau Institute of Systems Engineering Macau University of Science and Technology Macau China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Ningbo Sanbody Intelligent Technology co. LTD Ningbo China Faculty of Science and Engineering University of Nottingham Ningbo China

Along with economic globalization, the shoes and clothing market is undergoing huge changes and is facing increasing individualized demands. To realize personalized customization, we propose a social manufacturing pattern for the shoes and clothing industry. On the customer side, we collect costumer information with the help of 3D scanning and virtual fitting. On the production side, we replace human labor with intelligent production equipment. On the enterprise management side, we construct a cloud platform to realize source maximization. Through this social manufacturing pattern, we expect to accelerate the intelligent reform of the shoes and clothing industry.

关键词： Product customization Cloud computing Three-dimensional displays Social networking (online) Production equipment Footwear Clothing industry

来源：评论

学校读者我要写书评

暂无评论

Parallel Medical Imaging: An ACP-Based Approach for Intelligent Medical Image Recognition with Small Samples

Parallel Medical Imaging: An ACP-Based Approach for Intellig...

引用

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

作者： Tianyu Shen Chao Gou Jiangong Wang Jun Huang Yonglan He Huadan Xue Zhengyu Jin Fei-Yue Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Shenzhen Campus of Sun Yat-sen University Sun Yat-sen University Guangzhou China Peking Union Medical College Hospital Chinese Academy of Medical Sciences Peking Union Medical College Beijing China

The deep learning methods trained with large-scale manually annotated datasets have led to significant breakthroughs in medical image community. However, obtaining such datasets remains a challenging work in medical domain. In this paper, we propose an ACP-based approach named parallel medical imaging (PMI) for analyzing and addressing the small sample problem of medical image recognition. Firstly, we present the basic framework and key techniques of PMI, in which the Artificial imaging systems are constructed to effectively augment the “medical small sample”, the Computational experiments are carried out for designing and evaluating the visual models trained with small samples, and the Parallel execution is conducted to achieve closed-loop interaction and optimization in the domain-knowledge guidance. Furthermore, we illustrate a preliminary implementation and application of PMI approach through the case study of mammogram analysis.

关键词： Deep learning Visualization Image recognition Annotations Digital twin Conferences Computational modeling

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Federated control Strategy for Participant Selection in Multi-Client Collaboration

An Adaptive Federated Control Strategy for Participant Selec...

引用

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

作者： Yizhu Chen Xiaoming Du Xiao Wang Jun Jason Zhang Fei-Yue Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China School of Economics and Management University of Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China School of Electrical Engineering and Automation Wuhan University Wuhan China

The federated ecology provides a new paradigm for breaking the isolated data island problem and fully activating the potential of big data and artificial intelligence, especially in multi-client collaboration tasks. Participant selection strategy in multi-client collaboration is the main limitation for increasing the convergence speed and lowing the communication costs. However, in the face of the unbalanced and non-IID data distributions, the performance of federated optimization algorithms will also decrease. To solve the above problems, we propose an adaptive federated control strategy for participant selection in multi-client collaboration based on the Mann-Kendall test, named FedMK. By adaptively selecting weak participants for training rather than random selection, FedMK can speed up model convergence and reduce communication costs. Experiment results show that our method outperforms the baseline method in non-IID scenarios, and the number of communication rounds on CIFAR-10 and synthetic datasets reduced by more than 15% and 10 %,9 respectively.

关键词： Training Adaptation models Costs Biological system modeling Collaboration Optimization methods Ecology

来源：评论

学校读者我要写书评

暂无评论

MVM3Det: A novel method for multi-view monocular 3D detection

arXiv

引用

arXiv 2021年

作者： Li, Haoran Duan, Zicheng Ma, Mingjun Chen, Yaran Li, Jiaqi Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The University of Chinese Academy of Sciences Beijing China The College of Engineering and Computer Science Australian National University ACT2601 Australia The School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China

Monocular 3D object detection encounters occlusion problems in many application scenarios, such as traffic monitoring, pedestrian monitoring, etc., which leads to serious false negatives. Multi-view object detection effectively solves this problem by combining data from different perspectives. However, due to label confusion and feature confusion, the orientation estimation of multi-view 3D object detection is intractable, which is important for object tracking and intention prediction. In this paper, we propose a novel multi-view 3D object detection method named MVM3Det which simultaneously estimates the 3D position and orientation of the object according to the multi-view monocular information. The method consists of two parts: 1) Position proposal network, which integrates the features from different perspectives into consistent global features through feature orthogonal transformation to estimate the position. 2) Multi-branch orientation estimation network, which introduces feature perspective pooling to overcome the two confusion problems during the orientation estimation. In addition, we present the first dataset for multi-view 3D object detection named MVM3D. Comparing with state-Of-The-Art (SOTA) methods on our dataset and public dataset WildTrack, our method achieves very competitive results. © 2021, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Parallel Governance for Decentralized Autonomous Organizations enabled by Blockchain and Smart Contracts

Parallel Governance for Decentralized Autonomous Organizatio...

引用

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

作者： Wen Wen Ding XiaoLong Liang JiaChen Hou Ge Wang Yong Yuan Junqing Li Fei-Yue Wang Institute of Systems Engineering Macau University of Science and Technology Macau China School of Mathematics Renmin University of China Beijing China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Decentralized autonomous organizations(DAOs) enabled by blockchain and smart contracts is regarded as an effective tool to solve corporate governance problems. It can minimize the contract risks, principal-agent dilemmas, and other issues in corporate governance. However, DAOs also face a variety of governance issues, such as internal governance issues and external governance issues caused by the technical attributes of blockchain and smart contracts. DAO is a typical complex system with the characteristics of both social and engineering complexity. It is difficult for existing governance theories to solve governance problems in DAOs. The parallel intelligence theory based on the artificial systems + computational experiments + parallel execution (ACP) method is a suitable research and practical approach to solve management and control problems for complex systems. Therefore, we propose a parallel governance framework for DAO based on the parallel intelligence theory and discuss its key research issues. Finally, we construct a parallel governance system for GnosisDAO, and conduct computational experiments on its voting mechanism. The results show the defects of GnosisDAO governance mechanism and we thus propose further research directions. We consider that parallel governance represents the future trend of DAO research and practice. This paper is aimed at stimulating further effort and providing helpful guidance and reference for future research works.

关键词： Computational modeling Digital twin Conferences Smart contracts Tools systems modeling Market research

来源：评论

学校读者我要写书评

暂无评论

Muscle Synergy Analysis Based on NMF for Lower Limb Motor Function Assessment

Muscle Synergy Analysis Based on NMF for Lower Limb Motor Fu...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Kexin Xiang Weiqun Wang Zeng-Guang Hou Chutian Zhang Jiaxing Wang Weiguo Shi Yuze Jiao Tianyu Lin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China School of Artifificial Intelligence University of Chinese Academy of Sciences Beijing China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology Macao Macau Institute of Systems Engineering Macau University of Science and Technology Macau China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology China

ISBN: (纸本)9781665481106

Accurate rehabilitation assessments are essential for designing effective rehabilitation methods and helping patients recover better. It's well known that commonly used scale assessment methods for neurorehabilitation suffer from the issue of subjectivity, thus investigation of objective assessment methods is very necessary. Muscle synergy analysis can be uesd to assess limb motor functions from the perspective of neuromuscular control. In this paper, a method for evaluation of human lower limb motor functions based on muscle synergy analysis is presented. Muscle synergy modules are designed using surface electromyography (sEMG) signals of the subjects' lower limbs by non-negative matrix factorizations (NMF). By comparing the cosine similarities of these synergy modules, it can be seen that muscle synergies of healthy subjects and patients are significantly different, while they are similar among healthy subjects. Therefore, a reference synergy module (RSM) is designed by averaging the muscle synergy modules for healthy subjects, and the similarities can be calculated by comparing the synergy modules for healthy subjects or patients with the RSM. In the experiment carried out in this study, average similarities of the three synergy modules for healthy subjects are respectively 0.97166, 0.87368 and 0.84932, and on the other hand, the average similarities for the three synergy modules for patients are respectively 0.59979, 0.56426 and 0.69042. Therefore, the similarities for healthy subjects are much higher than those for SCI patients, which denotes that the similarity between an individual synergy module and the RSM can be used as an objective assessing index for evaluating patients' motor function.

关键词： Neuromuscular Biomimetics Stability criteria Muscles Electromyography Indexes Robots

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：