检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Noncontact Doppler Radar-based Heart Rate Detection on the SVD and ANC

Noncontact Doppler Radar-based Heart Rate Detection on the S...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qiuxia Shi Bin Hu Fuze Tian Qinglin Zhao Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University School of Computer and Communication Lanzhou University of Technology Ministry of Education Key Laboratory of Special Functional Materials and Structural Design (Lanzhou University) Lanzhou China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors Chinese Academy of Sciences Engineering Research Center of Open Source Software and Real-Time System(Lanzhou University) Ministry of Education Key Laboratory of Special Functional Materials and Structural Design Ministry of Education Lanzhou University Lanzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

In the Doppler biological radar-based applications of noncontact measurement of vital signs, effectively extracting heartbeat information from weak thoracic mechanical motion is an important problem to be solved. This study is aimed at extracting heartbeat signal via the technology combined with Short Time Fourier Transform (STFT), Singular Value Decomposition (SVD) and Adaptive Noise Canceller (ANC) from radar recording. The simulated data and the data collected by Doppler radar biosensor realized in laboratory are employed to validate the proposed method. The results show that the proposed method has the ability of detection for the heart rate and heart rate variability indexes in rest state, it has certain advantages in time-consuming and detection accuracy. Therefore, the current method provides another way to process vital sign signals recorded by Doppler radar.

关键词： Biomedical measurement Noise cancellation Time measurement Doppler radar Recording Doppler effect Biosensors

来源：评论

学校读者我要写书评

暂无评论

多肽靶向嵌合体通过促进tau蛋白特异性去磷酸化治疗阿尔茨海默病和其他tau蛋白病

引用

science Bulletin 2024年第8期69卷 1137-1152页

作者：苏静芬肖越魏林郁雷慧杨孙飞王围霞尹君熊瑞李师宏张配周颖王小川郑杰王建枝 Department of Pathophysiology School of Basic MedicineKey Laboratory of Education Ministry of China/Hubei Province for Neurological DisordersTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430030China Sino-UK Joint Laboratory of Brain Function and Injury of Henan Province Department of Physiology and PathophysiologySchool of Basic Medical SciencesXinxiang Medical UniversityXinxiang 453003China Department of Pathophysiology School of Basic Medical SciencesWuhan UniversityWuhan 430030China Department of Anesthesiology The First Affiliated Hospital of Gannan Medical UniversityGanzhou 341000China The Core Facility and Technical Support Wuhan Institute of VirologyChinese Academy of SciencesWuhan 430030China Research Center for Medicine and Structural Biology Wuhan UniversityWuhan 430030China Neuroscience Research Institute and Department of Neurobiology School of Basic Medical SciencesPeking UniversityKey Laboratory for NeuroscienceMinistry of Education/National Health CommissionBeijing 100083China Co-innovation Center of Neuroregeneration Nantong UniversityNantong 226000China

Abnormal hyperphosphorylation and accumulation of tau protein play a pivotal role in neurodegeneration in Alzheimer’s disease(AD)and many other *** elimination of hyperphosphorylated tau is promising for the therapy of these *** have conceptualized a strategy,named dephosphorylation-targeting chimeras(DEPTACs),for specifically hijacking phosphatases to tau to debilitate its ***,we conducted the step-by-step optimization of each constituent motif to generate DEPTACs with reasonable effectiveness in facilitating the dephosphorylation and subsequent clearance of pathological ***,for one of the selected chimeras,D16,we demonstrated its significant efficiency in rescuing the neurodegeneration caused by neurotoxic K18-tau seeds in ***,intravenous administration of D16 also alleviated tau pathologies in the brain and improved memory deficits in AD *** results suggested DEPTACs as targeted modulators of tau phosphorylation,which hold therapeutic potential for AD and other tauopathies.

关键词： tau Dephosphorylation-targeting chimeras Therapeutic potential Tauopathy

来源：评论

学校读者我要写书评

暂无评论

Inverse design of artificial skins

arXiv

引用

arXiv 2023年

作者： Liu, Zhiguang Cai, Minkun Hong, Shenda Shi, Junli Xie, Sai Liu, Chang Du, Huifeng Morin, James D. Li, Gang Liu, Wang Wang, Hong Tang, Ke Fang, Nicholas X. Guo, Chuan Fei Department of Materials Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Mechanical Engineering Massachusetts Institute of Technology CambridgeMA02139 United States National Institute of Health Data Science Peking University Beijing100191 China Centers for Mechanical Engineering Research Education at MIT and SUSTech Southern University of Science and Technology Shenzhen518055 China Department of Mechanical Engineering The University of Hong Kong Hong Kong999077 Hong Kong Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Modern Mechanics University of Science and Technology of China Hefei231600 China

Mimicking the perceptual functions of human cutaneous mechanoreceptors, artificial skins or flexible pressure sensors can transduce tactile stimuli to quantitative electrical signals1-3. Conventional methods to design such devices follow a forward structure-to-property routine based on trial-and-error experiments/simulations, which take months or longer to determine one solution valid for one specific material. Target-oriented inverse design that shows far higher output efficiency has proven effective in other fields4,5, but is still absent for artificial skins because of the difficulties in acquiring big data. Here, we report a property-to-structure inverse design of artificial skins based on small dataset machine learning, exhibiting a comprehensive efficiency at least four orders of magnitude higher than the conventional routine. The inverse routine can predict hundreds of solutions that overcome the intrinsic signal saturation problem for linear response in hours, and the solutions are valid to a variety of materials. Our results demonstrate that the inverse design allowed by small dataset is an efficient and powerful tool to target multifarious applications of artificial skins, which can potentially advance the fields of intelligent robots, advanced healthcare, and human-machine interfaces. Copyright © 2023, The Authors. All rights reserved.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Slow and weak attractor computation embedded in fast and strong E-I balanced neural dynamics 23

Slow and weak attractor computation embedded in fast and str...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xiaohan Lin Liyuan Li Boxin Shi Tiejun Huang Yuanyuan Mi Si Wu Nat'l Key Lab for Multimedia Information Processing Nat'l Eng. Lab of Visual Technology School of Computer Science Peking University and Peking-Tsinghua Center for Life Sciences Academy for Advanced Interdisciplinary Studies School of Psychological and Cognitive Sciences Beijing Key Laboratory of Behavior and Mental Health IDG/McGovern Institute for Brain Research Center of Quantitative Biology Peking University Department of Mathematics Peking University and Institute of Neuroinformatics University of Zurich Nat'l Key Lab for Multimedia Information Processing Nat'l Eng. Lab of Visual Technology School of Computer Science Peking University and Institute for Artificial Intelligence Peking University Department of Psychology Tsinghua University Peking-Tsinghua Center for Life Sciences Academy for Advanced Interdisciplinary Studies School of Psychological and Cognitive Sciences Beijing Key Laboratory of Behavior and Mental Health IDG/McGovern Institute for Brain Research Center of Quantitative Biology Peking University

Attractor networks require neuronal connections to be highly structured in order to maintain attractor states that represent information, while excitation and inhibition balanced networks (E-INNs) require neuronal connections to be random and sparse to generate irregular neuronal firing. Despite being regarded as canonical models of neural circuits, both types of networks are usually studied independently, and it remains unclear how they coexist in the brain, given their very different structural demands. In this study, we investigate the compatibility of continuous attractor neural networks (CANNs) and E-INNs. In line with recent experimental data, we find that a neural circuit can exhibit both the traits of CANNs and E-INNs when the neuronal synapses consist of two sets: one set is strong and fast for irregular firing, and the other set is weak and slow for attractor dynamics. In addition, both simulations and theoretical analysis reveal that the network exhibits enhanced performance compared to the case of using only one set of synapses, with accelerated convergence of attractor states and retained E-I balanced condition for localized input. We hope that this study provides insight into how structured neural computations are realized by irregular firings of neurons.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reference Vector Adaptation and Mating Selection Strategy via Adaptive Resonance Theory-based Clustering for Many-objective Optimization

arXiv

引用

arXiv 2022年

作者： Kinoshita, Takato Masuyama, Naoki Liu, Yiping Nojima, Yusuke Ishibuchi, Hisao Graduate School of Engineering Osaka Prefecture University 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan Graduate School of Informatics Osaka Metropolitan University 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan College of Computer Science and Electronic Engineering Hunan University Hunan 410082 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Decomposition-based multiobjective evolutionary algorithms (MOEAs) with clustering-based reference vector adaptation show good optimization performance for many-objective optimization problems (MaOPs). Especially, algorithms that employ a clustering algorithm with a topological structure (i.e., a network composed of nodes and edges) show superior optimization performance to other MOEAs for MaOPs with irregular Pareto optimal fronts (PFs). These algorithms, however, do not effectively utilize information of the topological structure in the search process. Moreover, the clustering algorithms typically used in conventional studies have limited clustering performance, inhibiting the ability to extract useful information for the search process. This paper proposes an adaptive reference vector-guided evolutionary algorithm using an adaptive resonance theory-based clustering with a topological structure. The proposed algorithm utilizes the information of the topological structure not only for reference vector adaptation but also for mating selection. The proposed algorithm is compared with 8 state-of-the-art MOEAs on 78 test problems. Experimental results reveal the outstanding optimization performance of the proposed algorithm over the others on MaOPs with various properties. © 2022, CC BY-NC-ND.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Low-resolution face recognition in the wild via selective knowledge distillation

arXiv

引用

arXiv 2018年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Li, Jia Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security at University of Chinese Academy of Sciences China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively. The teacher stream is represented by a complex CNN for high-accuracy recognition, and the student stream is represented by a much simpler CNN for low-complexity recognition. To avoid significant performance drop at the student stream, we then selectively distil the most informative facial features from the teacher stream by solving a sparse graph optimization problem, which are then used to regularize the fine-tuning process of the student stream. In this way, the student stream is actually trained by simultaneously handling two tasks with limited computational resources: approximating the most informative facial cues via feature regression, and recovering the missing facial cues via low-resolution face classification. Experimental results show that the student stream performs impressively in recognizing low-resolution faces and costs only 0.15MB memory and runs at 418 faces per second on CPU and 9, 433 faces per second on GPU. Copyright © 2018, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency

arXiv

引用

arXiv 2019年

作者： Li, Jia Fu, Kui Zhao, Shengwei Ge, Shiming State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security at University of Chinese Academy of Sciences Beijing100095 China

—The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model. The knowledge of spatial and temporal saliency is first separately transferred from the two complex and redundant teachers to their simple and compact students, and the input scenes are also degraded from high-resolution to low-resolution to remove the probable data redundancy so as to greatly speed up the feature extraction process. After that, the desired spatiotemporal model is further trained by distilling and encoding the spatial and temporal saliency knowledge of two students into a unified network. In this manner, the inter-model redundancy can be further removed for the effective estimation of dynamic saliency on aerial videos. Experimental results show that the proposed approach outperforms ten state-of-the-art models in estimating visual saliency on aerial videos, while its speed reaches up to 28,738 FPS on the GPU platform. Copyright © 2019, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A survey of deep learning-based classification methods for steady-state visual evoked potentials

引用

brain-Apparatus Communication: A Journal of Bacomics 2023年第1期2卷

作者： Yudong Pan Jianbo Chen Yangsong Zhang a School of Computer Science and Technology Laboratory for Brain Science and Medical Artificial Intelligence Southwest University of Science and Technology Mianyang P.R. China a School of Computer Science and Technology Laboratory for Brain Science and Medical Artificial Intelligence Southwest University of Science and Technology Mianyang P.R. Chinab MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu P.R. China

PurposeSteady-state visual evoked potential (SSVEP) based BCI has attracted great interests owing to the high information transfer rate (ITR) and little training requirement. The performance of SSVEP-based BCI heavily depends on the classification methods. Deep Learning (DL) technology provides an alternative avenue for the data classification in SSVEP-based BCI, and has received increasing interests in recent years. This review aimed to summarize the progress of DL-based classification methods for SSVEP data over the past *** and methodThe literature was searched and selected based on the research topics of DL and SSVEP. We categorized these methods into four classes, i.e., traditional neural network structures-based DL methods, traditional frequency recognition methods inspiring DL methods, attention mechanisms-based DL models, and transfer learning technology-based DL methods, and generative model-based recognition method. Moreover, we analyzed the current challenges and presented future research *** study provides a systematic description of the current development status on DL-based SSVEP classification methods, and sheds insight on future researches.

关键词： Deep learning (DL) brain-computer interface (BCI) steady-state visual evoked potential (SSVEP) frequency recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning

arXiv

引用

arXiv 2022年

作者： Masuyama, Naoki Amako, Narito Yamada, Yuna Nojima, Yusuke Ishibuchi, Hisao Graduate School of Informatics Osaka Metropolitan University 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan Graduate School of Engineering Osaka Prefecture University 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Adaptive Resonance Theory (ART) is considered as an effective approach for realizing continual learning thanks to its ability to handle the plasticity-stability dilemma. In general, however, the clustering performance of ART-based algorithms strongly depends on the specification of a similarity threshold, i.e., a vigilance parameter, which is data-dependent and specified by hand. This paper proposes an ART-based topological clustering algorithm with a mechanism that automatically estimates a similarity threshold from the distribution of data points. In addition, for improving information extraction performance, a divisive hierarchical clustering algorithm capable of continual learning is proposed by introducing a hierarchical structure to the proposed algorithm. Experimental results demonstrate that the proposed algorithm has high clustering performance comparable with recently-proposed state-of-the-art hierarchical clustering algorithms. © 2022, CC BY-NC-ND.

关键词： Clustering algorithms

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：