检索结果-内蒙古大学图书馆

FGDC: A fine-grained divide-and-conquer approach for extending NCO to solve large-scale Traveling Salesman Problem

Expert Systems with Applications 2025年 286卷

作者： Xinwei Chen Yurui Li Yifan Yang Li Zhang Shijian Li Gang Pan College of Computer Science and Technology Zhejiang University Hangzhou 310027 China Advanced Technology Research Institute Zhejiang University Hangzhou 310027 China State Key Laboratory of Brain-machine Intelligence Zhejiang University Hangzhou 310027 China

Large-scale Traveling Salesman Problem (TSP) applications are common and important in practice. Unfortunately, the time usage of the state-of-the-art heuristic solver LKH increases quadratically with the scale of the problem instance. Neural Combinatorial Optimization (NCO) has emerged as an efficient alternative to LKH, but it struggles to handle large-scale instances using zero-shot generalization. Divide-and-conquer is a classical paradigm for handling large-scale problems. However, integrating NCO with the divide-and-conquer paradigm is challenging. Fine-grained division is necessary to maintain the solution quality of the NCO solver on sub-problems. The K-Means algorithm is widely used for division as it delivers good results, but its time complexity grows to O ( N 2 ) in fine-grained division. Besides, merging strategies that rely on pre-defined rules miss opportunities to improve solution quality. In this paper, we present FGDC, a fine-grained divide-and-conquer approach for extending NCO to solve large-scale TSP. In the dividing procedure, we propose LocKMeans algorithm with O ( N ) time complexity to construct small-scale sub-problems based on the density distribution of nodes. The solving procedure imposes minimal constraints on the NCO solver, which is used to solve these sub-problems with GPU parallel execution, allowing FGDC to serve as a plug-and-play tool for general NCO approaches. We propose an MST-based merging strategy which is enhanced from three different perspectives including merging combination, merging operator, and merging order. Experimental results demonstrate that FGDC outperforms existing methods in the fine-grained division scenario. Additionally, it is highly scalable over instances ranging from 1K to 1M nodes. When employing POMO (pre-trained on TSP-100) as the solver, FGDC surpasses the SOTA baseline H-TSP by a significant margin, yielding the best result for large-scale TSP within the NCO landscape.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extending generalized unsupervised manifold alignment

引用

science China(Information sciences) 2022年第7期65卷 139-156页

作者： Xiaoyi YIN Zhen CUI Hong CHANG Bingpeng MA Shiguang SHAN Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences School of Computer Science and Engineering Nanjing University of Science and Technology CAS Center for Excellence in Brain Science and Intelligence Technology

Building connections between different data sets is a fundamental task in machine learning and related application community. With proper manifold alignment, the correspondences between data sets will assist us with comprehensive study of data processes and analyses. Despite the several progresses in semi-supervised and unsupervised scenarios, potent manifold alignment methods in generalized and realistic circumstances remain in absence. Besides, theretofore unsupervised algorithms seldom prove themselves mathematically. In this paper, we devise an efficient method to properly solve the unsupervised manifold alignment problem and denominate it as extending generalized unsupervised manifold alignment(EGUMA)method. More specifically, an explicit relaxed integer programming method is adopted to solve the unsupervised manifold alignment problem, which reconciles three factors covering the updated local structure matching, the the feature comparability and geometric preservation. An additional effort is retained on extending the Frank Wolfe algorithm to tacking our optimization problem. Besides our previous endeavors we adopt a new strategy for neighborhood discovery in the manifolds. The main advantages over previous methods accommodate(1) simultaneous alignment and discovery of manifolds;(2) complete unsupervised learning structure without any prerequisite correspondence;(3) more concise local geometry for the embedding space;(4) efficient alternative optimization;(5) strict mathematical analysis on the convergence and efficiency issues. Experiments on real-world applications verify the high accuracy and efficiency of our proposed method.

关键词： unsupervised manifold alignment relaxed integer programming Frank Wolfe algorithm

来源：评论

学校读者我要写书评

暂无评论

DSCT: a novel deep-learning framework for rapid and accurate spatial transcriptomic cell typing

引用

National science review 2025年第5期12卷 nwaf030页

作者： Yiheng Xu Bin Yu Xuan Chen Aibing Peng Quyuan Tao Youzhe He Yueming Wang Xiao-Ming Li Department of Neurology and Department of Psychiatry the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou 310058 China. NHC and CAMS Key Laboratory of Medical Neurobiology MOE Frontier Center of Brain Science and Brain-machine Integration School of Brain Science and Brain Medicine Zhejiang University Hangzhou 310058 China. College of Computer Science and Technology Zhejiang University Hangzhou 310000 China. Key Laboratory of Novel Targets and Drug Study for Neural Repair of Zhejiang Province Institute of brain and cognitive science Hangzhou City University School of Medicine Hangzhou 310015 China. Department of Neurobiology Affiliated Mental Health Center & Hangzhou Seventh People's Hospital Zhejiang University School of Medicine Hangzhou 310058 China. BGI Research Hangzhou 310030 China. Qiushi Academy for Advanced Studies Zhejiang University Hangzhou 310058 China. The Nanhu Brain-computer Interface institute Hangzhou 311100 China.

Unraveling complex cell-type-composition and gene-expression patterns at the cellular spatial resolution is crucial for understanding intricate cell functions in the brain. In this study, we developed Deep Neural Network-based Spatial Cell Typing (DSCT)-an innovative framework for spatial cell typing within spatial transcriptomic data sets. This approach utilizes a synergistic integration of an enhanced gene-selection strategy and a lightweight deep neural network for data training, offering a more rapid and accurate solution for the analysis of spatial transcriptomic data. Based on comprehensive analysis, DSCT achieved exceptional accuracy in cell-type identification across various brain regions, species and spatial transcriptomic platforms. It also performed well in mapping finer cell types, thereby showcasing its versatility and adaptability across diverse data sets. Strikingly, DSCT exhibited high efficiency and remarkable processing speed, with fewer computational resource demands. As such, this novel approach opens new avenues for exploring the spatial organization of cell types and gene-expression patterns, advancing our understanding of biological functions and pathologies within the nervous system.

关键词： DSCT deep-learning neural network spatial cell typing spatial transcriptomics

来源：评论

学校读者我要写书评

暂无评论

Current understanding of metal ions in the pathogenesis of Alzheimer’s disease

引用

Translational Neurodegeneration 2020年第2期9卷 105-117页

作者： Lu Wang Ya-Ling Yin Xin-Zi Liu Peng Shen Yan-Ge Zheng Xin-Rui Lan Cheng-Biao Lu Jian-Zhi Wang Key Laboratory of Brain Research of Henan Province Sino-UK Joint Laboratory of Brain Function and Injury of Henan ProvinceDepartment of Physiology and NeurobiologyXinxiang Medical UniversityXinxiang453003China Department of Pathophysiology School of Basic MedicineKey Laboratory of Ministry of Education of China for Neurological DisordersTongji Medical CollegeHuazhong University of Science and TechnologyWuhan430030China

Background The homeostasis of metal ions,such as iron,copper,zinc and calcium,in the brain is crucial for maintaining normal physiological *** have shown that imbalance of these metal ions in the brain is closely related to the onset and progression of Alzheimer’s disease(AD),the most common neurodegenerative disorder in the *** body Erroneous deposition/distribution of the metal ions in different brain regions induces oxidative *** metal ions imbalance and oxidative stress together or independently promote amyloid-β(Aβ)overproduction by activatingβ-orγ-secretases and inhibitingα-secretase,it also causes tau hyperphosphorylation by activating protein kinases,such as glycogen synthase kinase-3β(GSK-3β),cyclin-dependent protein kinase-5(CDK5),mitogen-activated protein kinases(MAPKs),etc.,and inhibiting protein phosphatase 2A(PP2A).The metal ions imbalances can also directly or indirectly disrupt organelles,causing endoplasmic reticulum(ER)stress;mitochondrial and autophagic dysfunctions,which can cause or aggravate Aβand tau aggregation/accumulation,and impair synaptic *** worse,the metal ions imbalance-induced alterations can reversely exacerbate metal ions misdistribution and *** vicious cycles between metal ions imbalances and Aβ/tau abnormalities will eventually lead to a chronic neurodegeneration and cognitive deficits,such as seen in AD *** The metal ions imbalance induces Aβand tau pathologies by directly or indirectly affecting multiple cellular/subcellular pathways,and the disrupted homeostasis can reversely aggravate the abnormalities of metal ions transportation/***,adjusting metal balance by supplementing or chelating the metal ions may be potential in ameliorating AD pathologies,which provides new research directions for AD treatment.

关键词： Metal ions Alzheimer's disease Amyloid-β Tau Oxidative stress Autophagy Synapses

来源：评论

学校读者我要写书评

暂无评论

Neural Control of Robotic Manipulator with Guaranteed Tracking Precision and Velocity Constraints 36

Neural Control of Robotic Manipulator with Guaranteed Tracki...

引用

第36届中国控制会议

作者： Min Wang Yanwen Zhang School of Automation Science and Engineering Guangzhou Key Laboratory of Brain Computer Interaction and ApplicationsSouth China University of Technology

ISBN: (纸本)9781538629185

This paper focuses on adaptive neural control design for n-link robot manipulator systems in the presence of tracking error and velocity state constraints.A performance function is utilized to characterize the prescribed performance of the tracking error.A new transformed function is used to guarantee that tracking errors satisfy the prescribed performance and the velocity states are not to violate their *** designed transformed function is not only of simple structure,but also overcomes the possible high-gain control problem caused by the existing transformed ***,a novel adaptive neural control scheme is proposed by combining independently Lyapunov functions *** proposed scheme guarantees all closed-loop signals are uniformly ultimately bounded,the output tracking errors satisfy the prescribed transient and steady-state tracking performances,and the velocity states are ensured to remain in the predefined bounded *** studies on a 2-link robot are performed and the effectiveness of the proposed scheme is illustrated by simulation results.

关键词： Adaptive Neural Control Tracking Error Constraints State Constraints Performance Transformation Robot Manipulators

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Dynamic Surface Control for Flexible Joint Manipulator with Prescribed Performance 29

Adaptive Neural Dynamic Surface Control for Flexible Joint M...

引用

第29届中国控制与决策会议

作者： Min Wang Huiping Ye School of Automation Science and Engineering Guangzhou Key Laboratory of Brain Computer Interaction and ApplicationsSouth China University of Technology

ISBN: (纸本)9781509046584

This paper focuses on adaptive neural control for a class of flexible joint manipulator with unknown dynamics under the output tracking error *** facilitate the design of control law,the constrained tracking error is transformed into unconstrained variable by introducing a performance function,the unknown dynamics of manipulator are accurately approximated by radial basis function(RBF) neural network(NN).Then,a novel adaptive neural control scheme is proposed using the derivative of the filter's output as the input of NN instead of traditional intermediate *** to structure features of the considered flexible joint manipulator,the proposed control scheme not only decreases the dimension of NN inputs,but also reduces the number of NN ***,it can be verified that all the signals in the closed-loop system are uniformly ultimately bounded and the constrained tracking error converges to a small neighborhood around zero with the prescribed *** results on a single-link flexible joint manipulator are given to illustrate the effectiveness of the proposed scheme.

关键词： Adaptive Neural Control Dynamic Surface Control Prescribed Performance Flexible Joint Manipulator

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Guided Refinement for Fine-Grained Salient Object Detection

arXiv

引用

arXiv 2025年

作者： Yuan, Yao Gao, Pan Dai, Qun Qin, Jie Xiang, Wei Collge of Computer Science and Technology Nanjing University of Aeronautics and Astronautics the Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing211106 China School of Computing Engineering and Mathematical Sciences La Trobe University MelbourneVIC3086 Australia

Recently, salient object detection (SOD) methods have achieved impressive performance. However, salient regions predicted by existing methods usually contain unsaturated regions and shadows, which limits the model for reliable fine-grained predictions. To address this, we introduce the uncertainty guidance learning approach to SOD, intended to enhance the model’s perception of uncertain regions. Specifically, we design a novel Uncertainty Guided Refinement Attention Network (UGRAN), which incorporates three important components, i.e., the Multilevel Interaction Attention (MIA) module, the Scale Spatial-Consistent Attention (SSCA) module, and the Uncertainty Refinement Attention (URA) module. Unlike conventional methods dedicated to enhancing features, the proposed MIA facilitates the interaction and perception of multilevel features, leveraging the complementary characteristics among multilevel features. Then, through the proposed SSCA, the salient information across diverse scales within the aggregated features can be integrated more comprehensively and integrally. In the subsequent steps, we utilize the uncertainty map generated from the saliency prediction map to enhance the model’s perception capability of uncertain regions, generating a highly-saturated fine-grained saliency prediction map. Additionally, we devise an adaptive dynamic partition (ADP) mechanism to minimize the computational overhead of the URA module and improve the utilization of uncertainty guidance. Experiments on seven benchmark datasets demonstrate the superiority of the proposed UGRAN over the state-of-the-art methodologies. Codes will be released at https://***/I2-Multimedia-Lab/UGRAN. Copyright © 2025, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multilabel Adversarial Examples: An Effective Black-Box Attack

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第3期4卷 562-572页

作者： Kong, Linghao Luo, Wenjian Zhang, Hongwei Liu, Yang Shi, Yuhui Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation School of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attack. Minor malicious modifications of examples will lead to the DNN misclassification. Such maliciously modified examples are called adversarial examples. So far, the work on adversarial examples is mainly focused on multiclass classification tasks;there is less work in the field of multilabel classification. In this article, for the first time, a differential evolution (DE) algorithm that can effectively generate multilabel adversarial examples is proposed, which is called MLAE-DE. Different from traditional DE, we designed a complementary mutation operator for MLAE-DE, which can improve attack performance and reduce the number of fitness evaluations. As a black-box attack, MLAE-DE does not need to access model parameters and only uses model outputs to generate adversarial examples. Experiments on two typical multilabel classification models and three typical datasets under the black-box settings are conducted in this article. Experimental results demonstrate that, comparing with the existing black-box attack algorithms for multilabel classification models, the attack success rate of our proposed algorithm is much better. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Two-step Thompson Sampling for Multi-Armed Bandit Problem

Two-step Thompson Sampling for Multi-Armed Bandit Problem

引用

第43届中国控制会议

作者： Zhigang Shang Lifang Yang Mengmeng Li School of Electrical and Information Engineering Zhengzhou University Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

An important feature of sequential decision-making under uncertain conditions is to strike a balance between exploration(obtaining information about the value of actions) and utilization(selecting the best action based on existing knowledge). The multi-armed bandit is a classic task for balancing their relationship. As the agent has learnt the relationship between two options in a 2-armed bandit task,it will no longer explore but instead use them directly. Inspired by the research, an algorithm based on two-step Thompson sampling(T-TS)is proposed to solve multi-armed bandit problem. First, posterior Beta distributions for the reward of each arm and the probability of the superior arm were established respectively. In the first-step TS, Thompson sampling was used to extract the maximum value from the posterior distribution of probability for the superior arm, determining it as the selected arm. In the two-step TS, Thompson sampling was used to sample from the distributions of the reward. During the updating, the posterior distribution of the probability for the superior arm was updated based on observations including actions and reward, and the distribution of the reward was updated based on the reward feedback. We performed the comparative experiments to solve the static multi-bandit tasks with 10, 20, 40, and 80 arms respectively by the state-of-the-art B-UCB algorithm, Thompson sampling and the proposed T-TS. The results shown that our proposed T-TS can learn the superior action more quickly with the best robustness.

关键词： Thompson sampling multi-armed bandit Beta distribution cumulative regret cumulative reward

来源：评论

学校读者我要写书评

暂无评论

Lifespan music training experience changes duration and transition rates of EEG microstates related to working memory

引用

brain-Apparatus Communication: A Journal of Bacomics 2025年第1期4卷

作者： Yan Li Sijia Guo Jiaxian Chen Liangfeng Feng Haoyu Bian Yuxin Chen Hua Yang Jing Lu a The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu Chinab School of Life Science and Technology Center for Information in Medicine University of Electronic Science and Technology of China Chengdu China a The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu Chinac School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China d Department of Composition Sichuan Conservatory of Music Chengdu Chinae Key Laboratory for Music Digital Intelligence of Sichuan Sichuan Conservatory of Music Chengdu China

ObjectiveAging-related compensatory scaffolding has been suggested to appear in the prefrontal regions in response to challenges posed by declines in working memory and inhibitory control associated with age. Although the potential mechanism of music intervention in cognitive aging is unclear, its effectiveness in interfering with executive function has been widely proven. A reasonable hypothesis is that music intervention alleviates cognitive aging by affecting compensatory scaffolding related to the prefrontal *** recruited three groups of participants: young control, old control, and old musicians, and calculated EEG microstate parameters. We used the classic N-back paradigm to examine subjects’ working memory performance. We also correlated the results of EEG microstates with behavioral *** found a decrease in the duration of microstate D (which has a frontal-central maximum) in all old subjects, which was related to poorer working memory performance. Meanwhile, old musicians benefit from lifespan music training experience and exhibit an opposite alleviating trend to the age effect in this outcome. We also found changes in the transition rate between *** results reflect the compensatory scaffolding of the prefrontal regions for other system functions in the process of music intervention in cognitive aging.

关键词： Music training cognitive aging working memory EEG microstate

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：