检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Jianxin Fu, Xingcheng Sun, Qingyun Ji, Cheng Tan, Jiajun Wu, Jia Peng, Hao Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China School of Computing Macquarie University Sydney Australia

Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space, leading to the information loss of topological properties (e.g. hierarchy and circularity). Moreover, due to the topological heterogeneity (i.e., different densities across the graph structure) of graph data, they suffer from serious topological distortion problems. In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. To better preserve the topological properties, we approximate the discrete structure as a continuous Riemannian geometric manifold and generate negative samples efficiently from the wrapped normal distribution. To deal with the topological heterogeneity, we leverage the Ricci curvature for local structures with different topological properties, obtaining to low-distortion representations. Extensive experiments show that CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks and shows superior robustness and generalization. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Collaborative Aggregation Networks for Multi-Site brain Disorder Diagnosis

Personalized Federated Learning with Collaborative Aggregati...

引用

Industrial Automation, Robotics and Control Engineering (IARCE), International Conference on

作者： Qian Si Yang Li School of Cyber Science and Technology Beihang University Beijing China Department of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Virtual Reality Technology and Systems Advanced Institute of Information Technology Peking University Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

In multi-site brain disease diagnosis studies, traditional centralized training methods necessitate sharing medical data, posing significant privacy risks. Federated learning (FL) offers a privacy-preserving solution by enabling global model training through aggregating locally trained models from multiple data centers without sharing raw data. However, current FL approaches rely on a server-based network topology, where central server failure disrupts training. Additionally, data heterogeneity across sites often slows convergence and reduces accuracy. To overcome these issues, we introduce a decentralized personalized federated learning collaborative aggregation network (pFedCAN). This framework has two core components: (1) separating local models into shared and personalized layers, and (2) forming a collaborative aggregation network via similarity detection in the shared layers. Specifically, each center trains its local model, then separates it into shared and personalized layers. The shared layer is exchanged with other centers, while the personalized layer remains local. data centers analyze similarities in received shared layers to build a collaborative network, where shared layers from similar centers are aggregated to refine the model. This approach flexibly adapts to varying levels of data heterogeneity, enhancing model training efficiency. Validation on public datasets, ABIDE I and ADHD, shows that the proposed method outperforms current leading techniques.

关键词： Training Adaptation models data centers Federated learning Service robots Collaboration brain modeling data models Servers Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Fast Robot Hierarchical Exploration Based on Deep Reinforcement Learning

Fast Robot Hierarchical Exploration Based on Deep Reinforcem...

引用

International Wireless Communications and Mobile computing Conference, IWCMC

作者： Shun Zuo Jianwei Niu Lu Ren Zhenchao Ouyang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Beijing China Beihang Hangzhou Innovation Institute Yuhang Beihang University Beijing China

This paper investigates the use of reinforcement learning for autonomous exploration in an unknown environment. Autonomous exploration is crucial in many situations, such as urban search, security inspection, environmental mapping, etc. Traditional approaches focused on frontiers are unlikely to span a variety of enormously complex scenarios. Convergence is a little more difficult for learning-based approaches, which can adapt to many different environments. Consequently, a hierarchical exploration framework is built using frontier information. We propose a reinforcement learning-based local decision exploration model that uses deep neural networks to learn the optimal strategy from the environment. To prevent falling into local optimization, we also suggest a global rescue module to assist the robot in returning to the proper exploration track. Compared with other hierarchical methods, the framework is more effective and resilient in many contexts, greatly decreasing the total completion time and path length.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous On-ramp Merge Strategy Using Deep Reinforcement Learning in Uncertain Highway Environment

Autonomous On-ramp Merge Strategy Using Deep Reinforcement L...

引用

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Wu, Sifan Tian, Daxin Zhou, Jianshan Duan, Xuting Sheng, Zhengguo Zhao, Dezong Beijing Key Laboratory For Cooperative Vehicle Infrastructure Systems&Safety Cooperative Control Beijing China Beijing Advanced Innovation Center For Big Data and Brain Computing Beijing China Department of Engineering and Design Richmond United Kingdom University of Sussex Richmond United Kingdom James Watt School of Engineering Glasgow United Kingdom University of Glasgow Glasgow United Kingdom

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

On-ramp merge is a complex traffic scenario in autonomous driving. Because of the uncertainty of the driving environment, most rule-based models cannot solve such a problem. In this study, we design a Deep Reinforcement Learning (DRL) method to solve the issue of ramp merges in uncertain scenarios and modify the structure of the Twin Delayed Deep Deterministic policy gradient algorithm (TD3), using Long Short-Term Memory (LSTM) to select an action based on temporal information. The proposed method is applied in the on-ramp merge and verified in the Simulation of Urban Mobility (SUMO). Results show that the proposed method performs significantly better generalization in uncertain traffic scenarios. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Low-loss Zero-index Waveguides and Devices

Low-loss Zero-index Waveguides and Devices

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Dong, Tian Dai, Tianxiang Chen, Ye Liu, Yueyang Liu, Hancheng Wang, Yiting Ma, Anqi Hu, Haifeng Xu, Lihua Zhao, Le Chu, Weiguo Peng, Chao Wang, Jianwei Li, Yang State Key Laboratory of Precision Measurement Technology and Instrument Department of Precision Instrument Tsinghua University Beijing100084 China State Key Laboratory for Mesoscopic Physics School of Physics Peking University Beijing100871 China State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Nanofabrication Laboratory National Center for Nanoscience and Technology Beijing100190 China

We report flexible zero-index waveguides and devices whose loss is two orders of magnitude lower than the state of the art, enabling phase-error-free high-dense photonic integrated circuits for classical and quantum i... 详细信息

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Low-loss Zero-index Waveguides and Devices

Low-loss Zero-index Waveguides and Devices

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Dong, Tian Dai, Tianxiang Chen, Ye Liu, Yueyang Liu, Hancheng Wang, Yiting Ma, Anqi Hu, Haifeng Xu, Lihua Zhao, Le Chu, Weiguo Peng, Chao Wang, Jianwei Li, Yang State Key Laboratory of Precision Measurement Technology and Instrument Department of Precision Instrument Tsinghua University Beijing100084 China State Key Laboratory for Mesoscopic Physics School of Physics Peking University Beijing100871 China State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics and Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Nanofabrication Laboratory National Center for Nanoscience and Technology Beijing100190 China

ISBN: (纸本)9781957171395

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

arXiv

引用

arXiv 2023年

作者： Sun, Kai Zhang, Richong Mensah, Samuel Aletras, Nikolaos Mao, Yongyi Liu, Xudong Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China Department of Computer Science University of Sheffield Sheffield United Kingdom School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios, where the testing and training distributions differ. Most methods use domain adversarial neural networks that aim to reduce the domain gap between the labelled source and unlabelled target domains to improve target domain performance. However, this approach only aligns feature distributions and does not account for class-wise feature alignment, leading to suboptimal results. Semi-supervised learning (SSL) has been explored as a solution, but is limited by the quality of pseudo-labels generated by the model. Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance. Extensive experiments on benchmark cross-domain OTE datasets show that this approach is effective and performs consistently well in settings with large domain shifts. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Channel-Augmented Multi-Domain Graph Convolutional Network for Fatigue Driving Detection

A Channel-Augmented Multi-Domain Graph Convolutional Network...

引用

Industrial Automation, Robotics and Control Engineering (IARCE), International Conference on

作者： Mingyi Sun Weigang Cui Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China School of Engineering Medicine Beihang University Beijing China Department of Automation Science and Electrical Engineering State Key Laboratory of Virtual Reality Technology and Systems The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Electroencephalography (EEG) has emerged as a crucial cornerstone within the realm of brain-computer interface (BCI) applications, with its significance notably pronounced in the field of fatigue detection. However, the inherent limitations of EEG acquisition equipment during real driving scenarios have contributed to the constrained robustness of existing models. Moreover, most of recent methods failed to extract robust multi-domain features, leading to a suboptimal performance. To address these challenges, we propose a novel channel-augmented multi-domain graph convolutional network (CA-MDGCNet). Specifically, the initial EEG signals are enriched by incorporating supplementary virtual EEG channels, distinguished as learnable parameters within the network architecture. Then, differential entropy features are extracted from the augmented EEG signals. Following this, a multi-domain graph convolutional network is designed to encode high-level EEG features by means of convolutions in diverse paths, which is beneficial to integrating the characteristics extracted from multiple domains. Finally, the classification block derives the detection outcome from the refined feature maps. To substantiate the potency of the proposed method, the validation was conducted on the publicly accessible SEED-VIG. The proposed CA-MDGCNet not only demonstrates more promising performance compared to state-of-the-art approaches but also underscores the potential viability of our method for the realm of fatigue driving detection.

关键词： Graph convolutional networks Convolution Service robots Neural activity Feature extraction Fatigue brain modeling Electroencephalography Entropy Robustness

来源：评论

学校读者我要写书评

暂无评论

Characteristic Decomposition: From Regular Sets to Normal Sets

引用

Journal of Systems Science & Complexity 2019年第1期32卷 37-46页

作者： MOU Chenqi WANG Dongming LMIB–School of Mathematics and Systems Science/Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University LMIB–SKLSDE–School of Mathematics and Systems Science/Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Centre National de la Recherche Scientifique

In this paper it is shown how to transform a regular triangular set into a normal triangular set by computing the W-characteristic set of their saturated ideal and an algorithm is proposed for decomposing any polynomial set into ?nitely many strong characteristic pairs, each of which is formed with the reduced lexicographic Gr?bner basis and the normal W-characteristic set of a characterizable ideal.

关键词： Characteristic decomposition characteristic pair normal set regular set W-characteristic set

来源：评论

学校读者我要写书评

暂无评论

brain-inspired artificial intelligence research: A review

引用

Science China(Technological Sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

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：