检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Sun, Li Zhang, Zhongbao Zhang, Jiawei Wang, Feiyang Peng, Hao Su, Sen Yu, Philip S. State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China IFM Lab Department of Computer Science Florida State University FL United States Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China Department of Computer Science University of Illinois ChicagoIL United States

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic graph representation in hyperbolic space, for the first time, which aims to infer stochastic node representations. Working with hyperbolic space, we present a novel Hyperbolic Variational Graph Neural Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach. To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions. Furthermore, we introduce a reparameterisable sampling algorithm for the hyperbolic normal distribution to enable the gradient-based learning of HVGNN. Extensive experiments show that HVGNN outperforms state-of-the-art baselines on real-world datasets. © 2021, CC BY-NC-SA.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Online Parameter Tuned SAHiD Algorithm for Capacitated Arc Routing Problems

Online Parameter Tuned SAHiD Algorithm for Capacitated Arc R...

引用

Congress on Evolutionary Computation

作者： Changwu Huang Yuanxiang Li Xin Yao Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation University Key Laboratory of Evolving Intelligent Systems of Guangdong Province Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (数字)9781728169293

ISBN: (纸本)9781728169309

The Capacitated Arc Routing Problem (CARP) is a general and challenging arc routing problem. As the problem size increasing, exact methods are not applicable, and heuristic and meta-heuristic algorithms are promising approaches to solve it. To obtain good performance, parameter values of heuristics or meta-heuristics should be properly set. In recent years, automatic parameter tuning, which includes off-line and online parameter tuning, has attracted considerable attention in the evolutionary computation community. At present, parameters are usually determined through simple off-line parameter tuning, such as empirical analysis or grid search, when designing algorithms for CARP. However, using off-line parameter tuning on CARP has some disadvantages, among which the computational cost is the serious one. This work proposed an online parameter tuning approach using exponential recency-weighted kernel density estimation (ERW-KDE), and combines it with the SAHiD algorithm, which is an hierarchical decomposition based algorithm for CARP, to constitute the online parameter tuned SAHiD (OPT-SAHiD) algorithm. The experimental results show that OPT-SAHiD significantly outperforms the compared algorithms on two CARP benchmark sets owing to the proposed online automatic parameter tuning approach. The proposed online automatic parameter tuning approach based on ERW-KDE not only improves the performance of SAHiD algorithm, but also removes the additional computational overhead required for offline parameter tuning.

关键词： Tuning Task analysis Heuristic algorithms Kernel Routing Estimation Probability density function

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Evolutionary Algorithm for Reliable Facility Location Problem

arXiv

引用

arXiv 2020年

作者： Zhang, Han Liu, Jialin Yao, Xin Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Secience and Engineering Southern University of Science and Technology Shenzhen518055 China

The reliable facility location problem (RFLP) is an important research topic of operational research and plays a vital role in the decision-making and management of modern supply chain and logistics. Through solving RFLP, the decision-maker can obtain reliable location decisions under the risk of facilities’ disruptions or failures. In this paper, we propose a novel model for the RFLP. Instead of assuming allocating a fixed number of facilities to each customer as in the existing works, we set the number of allocated facilities as an independent variable in our proposed model, which makes our model more close to the scenarios in real life but more difficult to be solved by traditional methods. To handle it, we propose EAMLS, a hybrid evolutionary algorithm, which combines a memorable local search (MLS) method and an evolutionary algorithm (EA). Additionally, a novel metric called l3-value is proposed to assist the analysis of the algorithm’s convergence speed and exam the process of evolution. The experimental results show the effectiveness and superior performance of our EAMLS, compared to a CPLEX solver and a Genetic Algorithm (GA), on large-scale problems. Copyright © 2020, The Authors. All rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Pathogen stress heightens sensorimotor dimensions in the human collective semantic space

Communications psychology

引用

Communications psychology 2025年第1期3卷 2页

作者： Ze Fu Huimin Chen Zhan Liu Maosong Sun Zhiyuan Liu Yanchao Bi State Key Laboratory of Cognitive Neuroscience and Learning & IDG/McGovern Institute for Brain Research Beijing Normal University Beijing 100875 China. School of Journalism and Communication Tsinghua University Beijing 100084 China. Department of Computer Science and Technology Tsinghua University Beijing 100084 China. Department of Computer Science and Technology Tsinghua University Beijing 100084 China. liuzy@***. State Key Laboratory of Cognitive Neuroscience and Learning & IDG/McGovern Institute for Brain Research Beijing Normal University Beijing 100875 China. ybi@***. School of Psychological and Cognitive Sciences and Beijing Key Laboratory of Behavior and Mental Health Peking University Beijing 100871 China. ybi@***. IDG/McGovern Institute for Brain Research Peking University Beijing 100871 China. ybi@***. Institute for Artificial Intelligence Peking University Beijing 100871 China. ybi@***. Chinese Institute for Brain Research Beijing 102206 China. ybi@***.

Infectious diseases have been major causes of death throughout human history and are assumed to broadly affect human psychology. However, whether and how conceptual processing, an internal world model central to various cognitive processes, adapts to such salient stress variables remains largely unknown. To address this, we conducted three studies examining the relationship between pathogen severity and semantic space, probed through the main neurocognitive semantic dimensions revealed by large-scale text analyses: one cross-cultural study (across 43 countries) and two historical studies (over the past 100 years). Across all three studies, we observed that increasing pathogen severity was associated with an enhancement of the sensory-motor dimension in the collective semantic space. These patterns remained robust after controlling for the effects of sociocultural variables, including economic wealth and societal norms of tightness. These results highlight the universal dynamic mechanisms of collective semantics, such that pathogen stress potentially drives sensorially oriented semantic processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision

arXiv

引用

arXiv 2021年

作者： Ji, Zhong Li, Jin Wang, Qiang Zhang, Zhongfei The School of Electrical and Information Engineering Tianjin University Tianjin300072 China The Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin University Tianjin300072 China The Computer Science Department Binghamton University State University of New York BinghamtonNY13902 United States

General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We reveal that the relation and feature deviations are crucial problems for catastrophic forgetting, in which relation deviation refers to the deficiency of the relationship among all classes in knowledge distillation, and feature deviation refers to indiscriminative feature representations. To this end, we propose a Complementary Calibration (CoCa) framework by mining the complementary model's outputs and features to alleviate the two deviations in the process of GCL. Specifically, we propose a new collaborative distillation approach for addressing the relation deviation. It distills model's outputs by utilizing ensemble dark knowledge of new model's outputs and reserved outputs, which maintains the performance of old tasks as well as balancing the relationship among all classes. Furthermore, we explore a collaborative self-supervision idea to leverage pretext tasks and supervised contrastive learning for addressing the feature deviation problem by learning complete and discriminative features for all classes. Extensive experiments on four popular datasets show that our CoCa framework achieves superior performance against state-of-the-art methods. © 2021, CC BY.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Diffusion Adaptive Filtering Algorithm Based on the Fair Cost Function

Research Square

引用

Research Square 2021年

作者： Guan, Sihai Cheng, Qing Zhao, Yong Biswal, Bharat College of Electronic and Information Southwest Minzu University China Key Laboratory of Electronic and Information Engineering State Ethnic Affairs Commission China Sichuan Vocational College of Finance and Economics Chengdu China School of Mechanical and Power Engineering Henan Polytechnic University Jiaozuo China The Clinical Hospital of Chengdu Brain Science Institute MOE Key Laboratory for Neuroinformation Center for Information in Medicine School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China NewarkNJ United States

To better perform distributed estimation, this paper, by combining the Fair cost function and adapt-then-combine scheme at all distributed network nodes, a novel diffusion adaptive estimation algorithm is proposed from an M-estimator perspective, which is called the diffusion Fair (DFair) adaptive filtering algorithm. The stability of the mean estimation error and the computational complexity of the DFair are theoretically analyzed. Compared with the RDLMS, DNLMM, DGCLD, and DPLMS algorithms, the simulation experiment results show that the DFair algorithm is more robust to input signals and impulsive interference. In conclusion, Theoretical analysis and simulation results show that the DFair algorithm performs better when estimating an unknown linear system in the changeable impulsive interference environments. © 2021, CC BY.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Predicting extreme events from data using deep machine learning: When and where

引用

Physical Review Research 2022年第2期4卷 023028-023028页

作者： Junjie Jiang Zi-Gang Huang Celso Grebogi Ying-Cheng Lai The Key Laboratory of Biomedical Information Engineering of Ministry of Education Institute of Health and Rehabilitation Science School of Life Science and Technology Research Center for Brain-inspired Intelligence Xi'an Jiaotong University The Key Laboratory of Neuro-informatics & Rehabilitation Engineering of Ministry of Civil Affairs Xi'an Shaanxi 710049 China School of Electrical Computer and Energy Engineering Arizona State University Tempe Arizona 85287 USA Institute for Complex Systems and Mathematical Biology School of Natural and Computing Sciences King's College University of Aberdeen Aberdeen AB24 3UE United Kingdom Department of Physics Arizona State University Tempe Arizona 85287 USA

We develop a framework based on the deep convolutional neural network (DCNN) for model-free prediction of the occurrence of extreme events both in time (“when”) and in space (“where”) in nonlinear physical systems of spatial dimension two. The measurements or data are a set of two-dimensional snapshots or images. For a desired time horizon of prediction, a proper labeling scheme can be designated to enable successful training of the DCNN and subsequent prediction of extreme events in time. Given that an extreme event has been predicted to occur within the time horizon, a space-based labeling scheme can be applied to predict, within certain resolution, the location at which the event will occur. We use synthetic data from the two-dimensional complex Ginzburg-Landau equation and empirical wind speed data from the North Atlantic Ocean to demonstrate and validate our machine-learning-based prediction framework. The trade-offs among the prediction horizon, spatial resolution, and accuracy are illustrated, and the detrimental effect of spatially biased occurrence of extreme events on prediction accuracy is discussed. The deep learning framework is viable for predicting extreme events in the real world.

关键词： Machine learning Spatiotemporal chaos Artificial neural networks Extreme event statistics

来源：评论

学校读者我要写书评

暂无评论

Finite time convergence of pinning synchronization with linear and nonlinear controllers

arXiv

引用

arXiv 2021年

作者： Lu, Wenlian Liu, Xiwei Chen, Tianping School of Mathematical Sciences Fudan University Shanghai200433 China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China Shanghai Key Laboratory for Contemporary Applied Mathematics Laboratory of Mathematics for Nonlinear Science Fudan University Shanghai200433 China Shanghai Center for Mathematical Sciences Fudan University Shanghai200433 China Department of Computer Science and Technology Tongji University Shanghai201804 China

In this paper, we propose several models, which can realize synchronization of complex networks in finite time effectively. The results apply to heterogeneous dynamic networks, too. The mechanism of finite time convergence is revealed. Different from many models, which assume the coupling matrix being symmetric (or the connecting graph is undirected), here, the coupling matrix is asymmetric (or the connecting graph is directed). Copyright © 2021, The Authors. All rights reserved.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Fast, accurate, and versatile data analysis platform for the quantification of molecular spatiotemporal signals

引用

Cell 2025年第10期188卷 2794-2809.e21页

作者： Mi, Xuelong Chen, Alex Bo-Yuan Duarte, Daniela Carey, Erin Taylor, Charlotte R. Braaker, Philipp N. Bright, Mark Almeida, Rafael G. Lim, Jing-Xuan Ruetten, Virginia M.S. Wang, Yizhi Wang, Mengfan Zhang, Weizhan Zheng, Wei Reitman, Michael E. Huang, Yongkang Wang, Xiaoyu Li, Lei Deng, HanFei Shi, Song-Hai Poskanzer, Kira E. Lyons, David A. Nimmerjahn, Axel Ahrens, Misha B. Yu, Guoqiang Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Arlington 22203 VA United States Janelia Research Campus Howard Hughes Medical Institute Ashburn 20147 VA United States Department of Molecular and Cellular Biology Harvard University Cambridge 02138 MA United States Graduate Program in Neuroscience Harvard Medical School Boston 02115 MA United States Waitt Advanced Biophotonics Center The Salk Institute for Biological Studies La Jolla 92037 CA United States Department of Biochemistry & Biophysics University of California San Francisco San Francisco CA United States Neuroscience Graduate Program University of California San Francisco San Francisco CA United States Centre for Discovery Brain Sciences University of Edinburgh Edinburgh BioQuarter Edinburgh EH16 4SB United Kingdom Gatsby Computational Neuroscience Unit UCL London W1T 4JG United Kingdom Kavli Institute for Fundamental Neuroscience San Francisco CA United States Department of Automation Tsinghua University Beijing 100084 China IDG/McGovern Institute for Brain Research Tsinghua University Beijing 100084 China New Cornerstone Science Laboratory Tsinghua-Peking Center for Life Sciences Beijing Frontier Research Center for Biological Structure School of Life Sciences Tsinghua University Beijing 100084 China State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University Shanghai 200032 China Beijing National Research Center for Information Science and Technology Beijing 100084 China

Optical recording of intricate molecular dynamics is becoming an indispensable technique for biological studies, accelerated by the development of new or improved biosensors and microscopy technology. This creates major computational challenges to extract and quantify biologically meaningful spatiotemporal patterns embedded within complex and rich data sources, many of which cannot be captured with existing methods. Here, we introduce activity quantification and analysis (AQuA2), a fast, accurate, and versatile data analysis platform built upon advanced machine-learning techniques. It decomposes complex live-imaging-based datasets into elementary signaling events, allowing accurate and unbiased quantification of molecular activities and identification of consensus functional units. We demonstrate applications across a wide range of biosensors, cell types, organs, animal models, microscopy techniques, and imaging approaches. As exemplar findings, we show how AQuA2 identified drug-dependent interactions between neurons and astroglia, as well as distinct sensorimotor signal propagation patterns in the mouse spinal cord. © 2025 The Author(s)

关键词： AQuA2 astrocytes cell interaction analysis functional units glial cells image analysis machine learning molecular spatiotemporal signals neurons time-lapse imaging

来源：评论

学校读者我要写书评

暂无评论

Real-time fine finger motion decoding for transradial amputees with surface electromyography

引用

Neural Networks 2025年 190卷 107605页

作者： Zihan Weng Yang Xiao Peiyang Li Chanlin Yi Pouya Bashivan Hailin Ma Guang Yao Yuan Lin Fali Li Dezhong Yao Jingming Hou Yangsong Zhang Peng Xu Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China 611731 Chengdu China School of Life Science and Technology Center for Information in Medicine University of Electronic Science and Technology of China 611731 Chengdu China College of Computer Science and Technology Chongqing University of Posts and Telecommunications 400065 Chongqing China School of Bioinformatics Chongqing University of Posts and Telecommunications 400065 Chongqing China Department of Physiology McGill University H3A 0G4 Montreal Canada Plateau Brain Science Research Center South China Normal University/Tibet University 850012 Lhasa China School of Materials and Energy State Key Laboratory of Electronic Thin Films and Integrated Devices University of Electronic Science and Technology of China 611731 Chengdu China Research Unit of NeuroInformation Chinese Academy of Medical Sciences 2019RU035 Chengdu China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macao Special Administrative Region of China School of Electrical Engineering Zhengzhou University 450001 Zhengzhou China Department of Rehabilitation Southwest Hospital Army Medical University 400038 Chongqing China School of Computer Science and Technology Laboratory for Brain Science and Medical Artificial Intelligence Southwest University of Science and Technology 621010 Mianyang China Radiation Oncology Key Laboratory of Sichuan Province 610041 Chengdu China Rehabilitation Center Qilu Hospital of Shandong University 250012 Jinan China

Advancements in human-machine interfaces (HMIs) are pivotal for enhancing rehabilitation technologies and improving the quality of life for individuals with limb loss. This paper presents a novel CNN-Transformer model for decoding continuous fine finger motions from surface electromyography (sEMG) signals by integrating the convolutional neural network (CNN) and Transformer architecture, focusing on applications for transradial amputees. This model leverages the strengths of both convolutional and Transformer architectures to effectively capture both local muscle activation patterns and global temporal dependencies within sEMG signals. To achieve high-fidelity sEMG acquisition, we designed a flexible and stretchable epidermal array electrode sleeve (EAES) that conforms to the residual limb, ensuring comfortable long-term wear and robust signal capture, critical for amputees. Moreover, we presented a computer vision (CV) based multimodal data acquisition protocol that synchronizes sEMG recordings with video captures of finger movements, enabling the creation of a large, labeled dataset to train and evaluate the proposed model. Given the challenges in acquiring reliable labeled data for transradial amputees, we adopted transfer learning and few-shot calibration to achieve fine finger motion decoding by leveraging datasets from non-amputated subjects. Extensive experimental results demonstrate the superior performance of the proposed model in various scenarios, including intra-session, inter-session, and inter-subject evaluations. Importantly, the system also exhibited promising zero-shot and few-shot learning capabilities for amputees, allowing for personalized calibration with minimal training data. The combined approach holds significant potential for advancing real-time, intuitive control of prostheses and other assistive technologies.

关键词： Convolutional neural networks Deep learning Fine motion decoding Human-machine interaction Surface electromyography Transformer

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：