检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Qi Wang, Huamin Shen, Hangchi Duan, Shukai Wen, Shiping Huang, Tingwen College of Artificial Intelligence Southwest University Chongqing400715 China Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips Chongqing400715 China College of Information Engineering University of Technology Sydney Australian Institute of Artificial Intelligence Sydney2007 Australia Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Recently, it can be noticed that most models based on spiking neural networks (SNNs) only use a same level temporal resolution to deal with speech classification problems, which makes these models cannot learn the information of input data at different temporal scales. Additionally, owing to the different time lengths of the data before and after the sub-modules of many models, the effective residual connections cannot be applied to optimize the training processes of these models. To solve these problems, on the one hand, we reconstruct the temporal dimension of the audio spectrum to propose a novel method named as Temporal Reconstruction (TR) by referring the hierarchical processing process of the human brain for understanding speech. Then, the reconstructed SNN model with TR can learn the information of input data at different temporal scales and model more comprehensive semantic information from audio data because it enables the networks to learn the information of input data at different temporal resolutions. On the other hand, we propose the Non-Aligned Residual (NAR) method by analyzing the audio data, which allows the residual connection can be used in two audio data with different time lengths. We have conducted plentiful experiments on the Spiking Speech Commands (SSC), the Spiking Heidelberg Digits (SHD), and the Google Speech Commands v0.02 (GSC) datasets. According to the experiment results, we have achieved the state-of-the-art (SOTA) result 81.02% on SSC for the test classification accuracy of all SNN models, and we have obtained the SOTA result 96.04% on SHD for the classification accuracy of all models. Furthermore, on the non-spiking dataset GSC, we can achieve a test classification accuracy of 95.63%, which surpasses the original baseline SNN-Delays. Meanwhile, the method proposed in this paper can speed up the model’s processing speed and reduce its energy consumption. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Detection of trace metals in water by filamentand plasma-grating-induced breakdown spectroscopy

引用

Advanced Photonics Nexus 2023年第1期2卷 70-79页

作者： Mengyun Hu Fangfang Li Shencheng Shi Yu Qiao Jinman Ge Xiaojun Li Heping Zeng East China Normal University State Key Laboratory of Precision SpectroscopyShanghaiChina Chongqing Institute of East China Normal University Chongqing Key Laboratory of Precision OpticsChongqingChina University of Shanghai for Science and Technology School of Optical-Electrical and Computer EngineeringEngineering Research Center of Optical Instrument and System(Ministry of Education)Shanghai Key Laboratory of Modern Optical SystemShanghaiChina China Academy of Space Technology(Xi’an) National Key Laboratory of Science and Technology on Space MicrowaveXi’anShaanxiChina Shanghai Research Center for Quantum Sciences ShanghaiChina Chongqing Institute for Brain and Intelligence Guangyang Bay LaboratoryChongqingChina

Filament-and plasma-grating-induced breakdown spectroscopy(F-GIBS)was demonstrated as an efficient technique for sensitive detection of metals in water,where plasma gratings were established through synchronized nonlinear interaction of two noncollinear filaments and an additional filament was generated with another fs laser beam propagating along their bisector.A water jet was constructed vertically to the three coplanar filaments,overcoming side effects from violent plasma explosion and bubble *** distinct regimes of different mechanisms were validated for nonlinear couplings of the third filament with plasma *** the third filament was temporally overlapped with the two noncollinear filaments in the interaction zone,all the three filaments participated in synchronous nonlinear interaction and plasma grating structures were altered by the addition of the third *** the third filament was positively or negatively delayed,the as-formed plasma gratings were elongated by the delayed third filament,or plasma gratings were formed in the presence of plasma expansion of the ahead third filament,*** F-GIBS for trace metal detection in water,significant spectral line enhancements were observed.

关键词： laser-induced breakdown spectroscopy filament and plasma-gratings induced breakdown spectroscopy filaments plasma gratings grating induced breakdown spectroscopy

来源：评论

学校读者我要写书评

暂无评论

BiKT: Unleashing the potential of GNNs via Bi-directional Knowledge Transfer

arXiv

引用

arXiv 2023年

作者： Zheng, Shuai Liu, Zhizhe Zhu, Zhenfeng Zhang, Xingxing Li, Jianxin Zhao, Yao The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Qiyuan Lab Beijing China The Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing100083 China

Based on the message-passing paradigm, there has been an amount of research proposing diverse and impressive feature propagation mechanisms to improve the performance of GNNs. However, less focus has been put on feature transformation, another major operation of the message-passing framework. In this paper, we first empirically investigate the performance of the feature transformation operation in several typical GNNs. Unexpectedly, we notice that GNNs do not completely free up the power of the inherent feature transformation operation. By this observation, we propose the Bi-directional Knowledge Transfer (BiKT), a plug-and-play approach to unleash the potential of the feature transformation operations without modifying the original architecture. Taking the feature transformation operation as a derived representation learning model that shares parameters with the original GNN, the direct prediction by this model provides a topological-agnostic knowledge feedback that can further instruct the learning of GNN and the feature transformations therein. On this basis, BiKT not only allows us to acquire knowledge from both the GNN and its derived model but promotes each other by injecting the knowledge into the other. In addition, a theoretical analysis is further provided to demonstrate that BiKT improves the generalization bound of the GNNs from the perspective of domain adaption. An extensive group of experiments on up to 7 datasets with 5 typical GNNs demonstrates that BiKT brings up to 0.5% - 4% performance gain over the original GNN, which means a boosted GNN is obtained. Meanwhile, the derived model also shows a powerful performance to compete with or even surpass the original GNN, enabling us to flexibly apply it independently to some other specific downstream tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

How do the resting EEG preprocessing states affect the outcomes of postprocessing?

arXiv

引用

arXiv 2023年

作者： Hu, Shiang Ruan, Jie Hou, Juan Valdes-Sosa, Pedro Antonio Lv, Zhao Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University 11 Jiulong Road Hefei230601 China Department of Psychology School of Philosophy Anhui University Hefei230601 China The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China Cuban Center for Neurocience La Habana Cuba

Plenty of artifact removal tools and pipelines have been developed to correct the EEG recordings and discover the values below the waveforms. Without visual inspection from the experts, it is susceptible to derive improper preprocessing states, like the insufficient preprocessed EEG (IPE), and the excessive preprocessed EEG (EPE). However, little is known about the impacts of IPE or EPE on the postprocessing in the frequency, spatial and temporal domains, particularly as to the spectra and the functional connectivity (FC) analysis. Here, the clean EEG (CE) was synthesized as the ground truth based on the New-York head model and the multivariate autoregressive model. Later, the IPE and the EPE were simulated by injecting the Gaussian noise and losing the brain activities, respectively. Then, the impacts on postprocessing were quantified by the deviation caused by the IPE or EPE from the CE as to the 4 temporal statistics, the multichannel power, the cross spectra, the dispersion of source imaging, and the properties of scalp EEG network. Lastly, the association analysis was performed between the PaLOSi metric and the varying trends of postprocessing with the evolution of preprocessing states. As results, compared with CE, it was found that: 1) the temporal statistics under IPE and EPE deviated greatly with more noise injected or more brain activities discarded;2) the IPE power was higher but the EPE power was lower, and the IPE power was almost parallel to that of CE cross all frequencies, while the power difference between the EPE and the CE decreased with higher frequencies;the cross spectra of IPE generally deviated more greatly than the EPE, except for the beta band;3) derived from the 7 Coupling measures, the IPE network had lower transmission efficiency and worse integration ability, while the EPE network had high transmission efficiency and better integration ability. 4) the source activation under IPE distributed more dispersedly with greater strength while t

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Subject inefficiency phenomenon of motor imagery brain-computer interface: Influence factors and potential solutions

引用

brain science Advances 2020年第3期6卷 224-241页

作者： Rui Zhang Fali Li Tao Zhang Dezhong Yao Peng Xu Henan Key Laboratory of Brain Science and Brain‐Computer Interface Technology School of Electrical EngineeringZhengzhou UniversityZhengzhou 450001HenanChina MOE Key Lab for NeuroInformation University of Electronic Science and Technology of ChinaChengdu 611731SichuanChina Science of School Xihua UniversityChengdu 610039SichuanChina

Motor imagery brain–computer interfaces(MI-BCIs)have great potential value in prosthetics control,neurorehabilitation,and gaming;however,currently,most such systems only operate in controlled laboratory *** of the most important obstacles is the MI-BCI inefficiency *** accuracy of MI-BCI control varies significantly(from chance level to 100%accuracy)across subjects due to the not easily induced and unstable MI-related EEG *** MI-BCI inefficient subject is defined as a subject who cannot achieve greater than 70%accuracy after sufficient training time,and multiple survey results indicate that inefficient subjects account for 10%–50%of the experimental *** widespread use of MI-BCI has been seriously limited due to these large percentages of inefficient *** this review,we summarize recent findings of the cause of MI-BCI inefficiency from resting-state brain function,task-related brain activity,brain structure,and psychological *** factors help understand the reasons for inter-subject MI-BCI control performance variability,and it can be concluded that the lower resting-state sensorimotor rhythm(SMR)is the key factor in MI-BCI inefficiency,which has been confirmed by multiple independent *** then propose to divide MI-BCI inefficient subjects into three categories according to the resting-state SMR and offline/online accuracy to apply more accurate approaches to solve the inefficiency *** potential solutions include developing transfer learning algorithms,new experimental paradigms,mindfulness meditation practice,novel training strategies,and identifying new motor imagery-related EEG *** date,few studies have focused on improving the control accuracy of MI-BCI inefficient subjects;thus,we appeal to the BCI community to focus more on this research *** by reducing the percentage of inefficient subjects can we create the opportunity to expand the value and influence of MI-BCI.

关键词： motor imagery brain-computer interface(MI-BCI) inefficient BCI user EEG indicator brain structure transfer learning

来源：评论

学校读者我要写书评

暂无评论

Biomedical data and AI

引用

science China Life sciences 2025年第5期68卷 1536-1540页

作者： Hao Xu Shibo Zhou Zefeng Zhu Vincenzo Vitelli Liangyi Chen Ziwei Dai Ning Yang Luhua Lai Shengyong Yang Sergey Ovchinnikov Zhuoran Qiao Sirui Liu Chen Song Jianfeng Pei Han Wen Jianfeng Feng Yaoyao Zhang Zhengwei Xie Yang-Yu Liu Zhiyuan Li Fulai Jin Hao Li Mohammad Lotfollahi Xuegong Zhang Ge Yang Shihua Zhang Ge Gao Pulin Li Qi Liu Jing-Dong Jackie Han Peking-Tsinghua Center for Life Sciences (CLS) Academy for Advanced Interdisciplinary StudiesPeking University Center for Quantitative Biology (CQB) Academy for Advanced Interdisciplinary StudiesPeking University Peking University-Tsinghua University-National Institute of Biological Sciences Joint Graduate Program Academy for Advanced Interdisciplinary StudiesPeking University Department of Physics University of Chicago School of Life Sciences Southern University of Science and Technology Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies College of Chemistry and Molecular Engineering Peking University Department of Biotherapy Cancer Center and State Key Laboratory of BiotherapyWest China HospitalSichuan University Department of Biology Massachusetts Institute of Technology Lambic Therapeutics Inc. Changping Laboratory Al for Science Institute Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Department of Obstetrics and Gynecology West China Second University HospitalSichuan University Peking University International Cancer Institute and Peking University-Yunnan Baiyao International Medical Institute and State Key Laboratory of Natural and Biomimetic Drugs Department of Molecular and Cellular PharmacologySchool of Pharmaceutical SciencesPeking University Health Science CenterPeking University Channing Division of Network Medicine Department of MedicineBrigham and Women's Hospital and Harvard Medical School Center for Artificial Intelligence and Modeling the Carl R.Woese Institute for Genomic BiologyUniversity of Illinois Urbana-Champaign Department of Genetics and Genome Sciences School of Medicine and Department of Computer and Data Sciences and Department of Population and Quantitative Health SciencesCase Western Reserve University Department of Biochemistry and Biophysics University of California Sanger Institute Department of Automation Tsinghua University State Key Laboratory of Multimodal Artificial Intelligence Systems I

The development of artificial intelligence(AI) and the mining of biomedical data complement each other. From the direct use of computer vision results to analyze medical images for disease screening, to now integrating biological knowledge into models and even accelerating the development of new AI based on biological discoveries, the boundaries of both are constantly expanding, and their connections are becoming closer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resource-constrained federated edge learning with heterogeneous data: Formulation and analysis

arXiv

引用

arXiv 2021年

作者： Liu, Yi Zhu, Yuanshao Yu, James J.Q. The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Efficient collaboration between collaborative machine learning and wireless communication technology, forming a Federated Edge Learning (FEEL), has spawned a series of next-generation intelligent applications. However, due to the openness of network connections, the FEEL framework generally involves hundreds of remote devices (or clients), resulting in expensive communication costs, which is not friendly to resource-constrained FEEL. To address this issue, we propose a distributed approximate Newton-type algorithm with fast convergence speed to alleviate the problem of FEEL resource (in terms of communication resources) constraints. Specifically, the proposed algorithm is improved based on distributed L-BFGS algorithm and allows each client to approximate the high-cost Hessian matrix by computing the low-cost Fisher matrix in a distributed manner to find a "better" descent direction, thereby speeding up convergence. Second, we prove that the proposed algorithm has linear convergence in strongly convex and non-convex cases and analyze its computational and communication complexity. Similarly, due to the heterogeneity of the connected remote devices, FEEL faces the challenge of heterogeneous data and non-IID (Independent and Identically Distributed) data. To this end, we design a simple but elegant training scheme, namely FedOVA, to solve the heterogeneous statistical challenge brought by heterogeneous data. In this way, FedOVA first decomposes a multi-class classification problem into more straightforward binary classification problems and then combines their respective outputs using ensemble learning. In particular, the scheme can be well integrated with our communication efficient algorithm to serve FEEL. Numerical results verify the effectiveness and superiority of the proposed algorithm. © 2021, CC0.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Trust toward humans and trust toward artificial intelligence are not associated: Initial insights from self-report and neurostructural brain imaging

引用

Personality Neuroscience 2023年第1期6卷 e3-e3页

作者： Montag, Christian Klugah-Brown, Benjamin Zhou, Xinqi Wernicke, Jennifer Liu, Congcong Kou, Juan Chen, Yuanshu Haas, Brian W. Becker, Benjamin Department of Molecular Psychology Institute of Psychology and Education Ulm University Ulm Germany Clinical Hospital of Chengdu Brain Science Institute MOE Key Laboratory for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology Chengdu China Institute of Brain and Psychological Sciences Sichuan Normal University Chengdu China Department of Psychology Xinxiang Medical University Henan China Department of Psychology University of Georgia Athens GA United States

The present study examines whether self-reported trust in humans and self-reported trust in [(different) products with built-in] artificial intelligence (AI) are associated with one another and with brain structure. We sampled 90 healthy participants who provided self-reported trust in humans and AI and underwent brain structural magnetic resonance imaging assessment. We found that trust in humans, as measured by the trust facet of the personality inventory NEO-PI-R, and trust in AI products, as measured by items assessing attitudes toward AI and by a composite score based on items assessing trust toward products with in-built AI, were not significantly correlated. We also used a concomitant dimensional neuroimaging approach employing a data-driven source-based morphometry (SBM) analysis of gray-matter-density to investigate neurostructural associations with each trust domain. We found that trust in humans was negatively (and significantly) correlated with an SBM component encompassing striato-Thalamic and prefrontal regions. We did not observe significant brain structural association with trust in AI. The present findings provide evidence that trust in humans and trust in AI seem to be dissociable constructs. While the personal disposition to trust in humans might be hardwired to the brain's neurostructural architecture (at least from an individual differences perspective), a corresponding significant link for the disposition to trust AI was not observed. These findings represent an initial step toward elucidating how different forms of trust might be processed on the behavioral and brain level. © The Author(s), 2023. Published by Cambridge University Press.

关键词： Artificial intelligence MRI Trust

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective

arXiv

引用

arXiv 2024年

作者： Liu, Jingren Ji, Zhong Yu, YunLong Cao, Jiale Pang, Yanwei Han, Jungong Li, Xuelong School of Electrical and Information Engineering Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin University Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Computer Science The University of Sheffield United Kingdom China Telecom Corp Ltd 31 Jinrong Street Beijing100033 China

Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate continual performance in this paradigm remains elusive. To tackle this complexity, we undertake a rigorous analysis of PEFT-CL dynamics to derive relevant metrics for continual scenarios using Neural Tangent Kernel (NTK) theory. With the aid of NTK as a mathematical analysis tool, we recast the challenge of test-time forgetting into the quantifiable generalization gaps during training, identifying three key factors that influence these gaps and the performance of PEFT-CL: training sample size, task-level feature orthogonality, and regularization. To address these challenges, we introduce NTK-CL, a novel framework that eliminates task-specific parameter storage while adaptively generating task-relevant features. Aligning with theoretical guidance, NTK-CL triples the feature representation of each sample, theoretically and empirically reducing the magnitude of both task-interplay and task-specific generalization gaps. Grounded in NTK analysis, our approach imposes an adaptive exponential moving average mechanism and constraints on task-level feature orthogonality, maintaining intra-task NTK forms while attenuating inter-task NTK forms. Ultimately, by fine-tuning optimizable parameters with appropriate regularization, NTK-CL achieves state-of-the-art performance on established PEFT-CL benchmarks. This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Combinatorial Optimization via Heat Diffusion

arXiv

引用

arXiv 2024年

作者： Ma, Hengyuan Lu, Wenlian Feng, Jianfeng Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Ministry of Education China School of Mathematical Sciences Fudan University No. 220 Handan Road Shanghai Shanghai200433 China Shanghai Center for Mathematical Sciences No. 220 Handan Road Shanghai Shanghai200433 China Shanghai Key Laboratory for Contemporary Applied Mathematics No. 220 Handan Road Shanghai Shanghai200433 China Key Laboratory of Mathematics for Nonlinear Science No. 220 Handan Road Shanghai Shanghai200433 China Department of Computer Science University of Warwick CoventryCV4 7AL United Kingdom

Combinatorial optimization problems are widespread but inherently challenging due to their discrete nature. The primary limitation of existing methods is that they can only access a small fraction of the solution space at each iteration, resulting in limited efficiency for searching the global optimal. To overcome this challenge, diverging from conventional efforts of expanding the solver’s search scope, we focus on enabling information to actively propagate to the solver through heat diffusion. By transforming the target function while preserving its optima, heat diffusion facilitates information flow from distant regions to the solver, providing more efficient navigation. Utilizing heat diffusion, we propose a framework for solving general combinatorial optimization problems. The proposed methodology demonstrates superior performance across a range of the most challenging and widely encountered combinatorial optimizations. Echoing recent advancements in harnessing thermodynamics for generative artificial intelligence, our study further reveals its significant potential in advancing combinatorial optimization. The codebase of our study is available in https://***/AwakerMhy/HeO. © 2024, CC BY.

关键词： Combinatorial optimization

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：