检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gu, Shi Mattar, Marcelo G. Tang, Huajin Pan, Gang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China Psychology Department New York University United States College of Computer Science and Technology Zhejiang University Hangzhou China State Key Laboratory of Brain Machine Intelligence Zhejiang University Hangzhou China

While advances in artificial intelligence and neuroscience have enabled the emergence of neural networks capable of learning a wide variety of tasks, our understanding of the temporal dynamics of these networks remains limited. Here, we study the temporal dynamics during learning of Hebbian Feedforward (HebbFF) neural networks in tasks of continual familiarity detection. Drawing inspiration from the field of network neuroscience, we examine the network's dynamic reconfiguration, focusing on how network modules evolve throughout learning. Through a comprehensive assessment involving metrics like network accuracy, modular flexibility, and distribution entropy across diverse learning modes, our approach reveals various previously unknown patterns of network reconfiguration. In particular, we find that the emergence of network modularity is a salient predictor of performance, and that modularization strengthens with increasing flexibility throughout learning. These insights not only elucidate the nuanced interplay of network modularity, accuracy, and learning dynamics but also bridge our understanding of learning in artificial and biological realms. © 2023, CC BY.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning

arXiv

引用

arXiv 2024年

作者： Ming, Yuhang Xu, Minyang Yang, Xingrui Ye, Weicai Wang, Weihan Peng, Yong Dai, Weichen Kong, Wanzeng School of Computer Science Hangzhou Dianzi University Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province Hangzhou310018 China High-speed Aerodynamics Institute CARDC Mianyang621000 China State Key Lab of CAD&CG Zhejiang University Hangzhou310058 China Stevens Institute of Technology HobokenNJ07030 United States

Visual place recognition (VPR) is essential to many autonomous systems. Existing VPR methods demonstrate attractive performance at the cost of limited generalizability. When deployed in unseen environments, these methods exhibit significant performance drops. Targeting this issue, we present VIPeR, a novel approach for visual incremental place recognition with the ability to adapt to new environments while retaining the performance of previous ones. We first introduce an adaptive mining strategy that balances the performance within a single environment and the generalizability across multiple environments. Then, to prevent catastrophic forgetting in continual learning, we design a novel multi-stage memory bank for explicit rehearsal. Additionally, we propose a probabilistic knowledge distillation to explicitly safeguard the previously learned knowledge. We evaluate our proposed VIPeR on three large-scale datasets—Oxford Robotcar, Nordland, and TartanAir. For comparison, we first set a baseline performance with naive finetuning. Then, several more recent continual learning methods are compared. Our VIPeR achieves better performance in almost all aspects with the biggest improvement of 13.85% in average performance. 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

ESVAE: An Efficient Spiking Variational Autoencoder with Reparameterizable Poisson Spiking Sampling

arXiv

引用

arXiv 2023年

作者： Zhan, Qiugang Tao, Ran Xie, Xiurui Liu, Guisong Zhang, Malu Tang, Huajin Yang, Yang The Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu611130 China The Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China Chengdu611731 China The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China The College of Computer Science The State Key Laboratory of Brain-Machine Intelligence Zhejiang University Hangzhou310027 China

In recent years, studies on image generation models of spiking neural networks (SNNs) have gained the attention of many researchers. Variational autoencoders (VAEs), as one of the most popular image generation models, have attracted a lot of work exploring their SNN implementation. Due to the constrained binary representation in SNNs, existing SNN VAE methods implicitly construct the latent space by an elaborated autoregressive network and use the network outputs as the sampling variables. However, this unspecified implicit representation of the latent space will increase the difficulty of generating high-quality images and introduce additional network parameters. In this paper, we propose an efficient spiking variational autoencoder (ESVAE) that constructs an interpretable latent space distribution and designs a reparameterizable spiking sampling method. Specifically, we construct the prior and posterior of the latent space as a Poisson distribution using the firing rate of the spiking neurons. Subsequently, we propose a reparameterizable Poisson spiking sampling method, which is free from the additional network. Comprehensive experiments have been conducted, and the experimental results show that the proposed ESVAE outperforms previous SNN VAE methods in reconstructed & generated image quality. In addition, experiments demonstrate that the encoder of ESVAE can retain the original image information more efficiently and is more robust. The source code is available at https://***/QgZhan/ESVAE. Copyright © 2023, The Authors. All rights reserved.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

The Capacity of Skin Potential in Generalized Anxiety Disorder Discrimination Using Weighted Feature Fusion

SSRN

引用

SSRN 2024年

作者： Sun, Jing Chen, Mingtao Sun, Jingxuan Rao, Shuying Zhang, Yaoyun Zhao, Sha Pan, Gang Jiang, Haiteng Li, Tao Affiliated Mental Health Center Hangzhou Seventh People's Hospital School of Brain Science and Brain Medicine Zhejiang University School of Medicine Hangzhou310058 China College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China Liangzhu Laboratory MOE Frontier Science Center for Brain Science and Brain-machine Integration State Key Laboratory of Brain-machine Intelligence Zhejiang University 1369 West Wenyi Road Hangzhou311121 China School of Biomedical Informatics University of Texas at Dallas 800 W Campbell Rd RichardsonTX75080 United States College of Computer Science and Technology Zhejiang University Hangzhou310013 China NHC CAMS Key Laboratory of Medical Neurobiology Zhejiang University Hangzhou310058 China

Background: In today's high-pressure society, anxiety disorders have come to the forefront of public attention. Distinguishing anxiety disorders accurately, conveniently, and effectively is of immense social value and scientific ***: Thirty-one generalized anxiety disorder (GAD) patients and twenty healthy controls (HC) were recruited in this study, and skin potential (SP) signals were collected during the resting state and task state using a single-channel portable device. Time-domain, spectral-domain, and nonlinear features were extracted from these two states, and feature coefficients were obtained by examining the relationship between individual features and clinical scales. Furthermore, single-mode features (resting state or task state), bimodal features (both two states with direct feature combination) and fused bimodal features (both two states with weighted feature coefficients) were fed into multiple machine learning algorithms including support vector machine (SVM), decision trees (DT), random forest (RF), and cat boost (CB) to distinguish between these two groups at the individual level. Model performances were systematically evaluated and compared using 10 fold ***: The weighted feature fusion approach achieved the best performance in individual GAD prediction (88.31%), comparing to single-mode features (resting state: 72.68%;task state: 79.07%) and direct feature combinations (84.57%). Conclusion: Our proposed weighted feature fusions from resting state and task state provides a promising tool to aid in early screening and clinical support in the GAD diagnosis. © 2024, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Exploring formal defeasible reasoning of large language models: A Chain-of-Thought approach

引用

Knowledge-Based Systems 2025年 319卷

作者： Li, Zhaoqun Chen, Chen Li, Mengze Liao, Beishui School of Philosophy Zhejiang University China College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence China

Defeasible reasoning, critical for commonsense reasoning and uncertainty handling, has garnered significant attention in AI community. This interest is particularly pronounced in the development and evaluation of Large Language Models (LLMs), which often involve reconciling inconsistent and incomplete knowledge. However, it remains uncertain whether LLMs possess generalizable defeasible reasoning abilities. Besides, the lack of a formal defeasible reasoning benchmark and appropriate evaluations limits further exploration in this domain. In this study, we aim to investigate the capacity of LLMs for defeasible reasoning, particularly within the framework of formal defeasible logic. Specifically, we select the popular defeasible logic framework, DeLP, as the basis for evaluating the LLMs’ defeasible logical reasoning capabilities. We initially create a synthetic dataset comprising logical programs that encompass a variety of DeLP programs with differing depths of reasoning. To address the challenges encountered during inference, we introduce a Chain-of-Thought (CoT) framework that prompts LLMs to conduct formal deduction and engage in multi-step defeasible reasoning, thereby enhancing problem-solving performance. Employing this argumentative solving approach, we observe that LLMs struggle to manage defeasible information effectively. This observation raises questions about whether contemporary LLMs possess reasoning abilities comparable to human intelligence, challenging the reliable deployment and advancement of AI systems in real-world scenarios. © 2025

关键词： Constraint programming

来源：评论

学校读者我要写书评

暂无评论

Scalable Electrophysiology of Millimeter-Scale Animals with Electrode Devices

引用

Biomedical Engineering Frontiers 2023年第1期4卷 3-20页

作者： Kairu Dong Wen-Che Liu Yuyan Su Yidan Lyu Hao Huang Nenggan Zheng John A.Rogers Kewang Nan College of Pharmaceutical Sciences Zhejiang UniversityHangzhou 310058China National Key Laboratory of Advanced Drug Delivery and Release Systems Zhejiang UniversityHangzhou 310058China College of Biomedical Engineering&Instrument Science Zhejiang UniversityHangzhou310027China Department of Gastroenterology Brigham and Women’s HospitalHarvard Medical SchoolBostonMA 02115USA College of Chemical and Biological Engineering Zhejiang UniversityHangzhou 310058China Qiushi Academy for Advanced Studies Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China State Key Lab of Brain-Machine Intelligence Zhejiang UniversityHangzhou 310058China CCAI by MOE and Zhejiang Provincial Government(ZJU) Hangzhou 310027China Querrey Simpson Institute for Bioelectronics Northwestern UniversityEvanstonIL 60208USA Department of Biomedical Engineering Northwestern UniversityEvanstonIL 60208USA Department of Materials Science and Engineering Northwestern UniversityEvanstonIL 60208USA Department of Mechanical Engineering Northwestern UniversityEvanstonIL 60208USA Jinhua Institute of Zhejiang University Jinhua 321299China

Millimeter-scale animals such as Caenorhabditis elegans,Drosophila larvae,zebrafish,and bees serve as powerful model organisms in the fields of neurobiology and *** methods exist for recording large-scale electrophysiological signals from these *** approaches often lack,however,real-time,uninterrupted investigations due to their rigid constructs,geometric constraints,and mechanical mismatch in integration with soft *** recent research establishes the foundations for 3-dimensional flexible bioelectronic interfaces that incorporate microfabricated components and nanoelectronic function with adjustable mechanical properties and multidimensional variability,offering unique capabilities for chronic,stable interrogation and stimulation of millimeter-scale animals and miniature tissue *** review summarizes the most advanced technologies for electrophysiological studies,based on methods of 3-dimensional flexible bioelectronics.A concluding section addresses the challenges of these devices in achieving freestanding,robust,and multifunctional biointerfaces.

关键词： offering recording millimeter

来源：评论

学校读者我要写书评

暂无评论

Kinetic and Kinematic Sensors-free Approach for Estimation of Continuous Force and Gesture in sEMG Prosthetic Hands

arXiv

引用

arXiv 2024年

作者： Liu, Gang Wang, Zhenxiang Xi, Chuanmei He, Ziyang Guo, Shanshan Zhang, Rui Yao, Dezhong School of Electrical and information Engineering Zhengzhou University Zhengzhou450001 China Henan Key Laboratory of Brain Science and Brain Computer Interface Technology Zhengzhou University Zhengzhou450001 China Engineering Department of International College Zhengzhou University 450001 China School of Cyber Science and Engineering Zhengzhou University Zhengzhou450000 China Shanghai Key Laboratory of Brain-Machine Intelligence for Information Behavior Shanghai International Studies University China Clinical Hospital of Chengdu Brain Science Institute MOE Key Laboratory for NeuroInformation University of Electronic Science and Technology of China Chengdu China Research Unit of NeuroInformation Chinese Academy of Medical Sciences Chengdu China

Regression-based sEMG prosthetic hands are widely used for their ability to provide continuous kinetic and kinematic parameters. However, establishing these models requires complex sensors systems to collect corresponding kinetic and kinematic data in synchronization with sEMG, which is cumbersome and user-unfriendly. This paper proposes a kinetic and kinematic sensors-free approach for controlling sEMG prosthetic hands, enabling continuous decoding and execution of three hand movements: individual finger flexion/extension, multiple finger flexion/extension, and fist opening/closing. This approach utilizes only two data points (-1 and 1), representing maximal finger flexion force label and extension force label respectively, and their corresponding sEMG data to establish a near-linear model based on sEMG data and labels. The model's output labels values are used to control the direction and magnitude of fingers forces, enabling the estimation of continuous gestures. To validate this approach, we conducted offline and online experiments using four models: Dendritic Net (DD), Linear Net (LN), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). The offline analysis assessed each model's ability to classify finger force direction and interpolate intermediate force values, while online experiments evaluated real-time control performance in controlling gestures and accurately adjusting forces. Our results demonstrate that the DD and LN models provide excellent real-time control of finger forces and gestures, highlighting the practical potential of this sensors-free approach for prosthetic applications. This study significantly reduces the complexity of collecting kinetic and kinematic parameters in sEMG-based regression prosthetics, thus enhancing the usability and convenience of prosthetic hands. © 2024, CC BY-NC-SA.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Visual commonsense reasoning with directional visual connections

引用

Frontiers of Information technology & Electronic Engineering 2021年第5期22卷 625-637页

作者： Yahong HAN Arning WU Linchao ZHU Yi YANG College of Intelligence and Computing Tianjin UniversityTianjin 300350China Tianjin Key Lab of Machine Learning Tianjin UniversityTianjin 300350China School of Computer Science University of Technology SydneySydney 2007Australia

To boost research into cognition-level visual understanding,i.e.,making an accurate inference based on a thorough understanding of visual details,visual commonsense reasoning(VCR)has been *** with traditional visual question answering which requires models to select correct answers,VCR requires models to select not only the correct answers,but also the correct *** research into human cognition has indicated that brain function or cognition can be considered as a global and dynamic integration of local neuron connectivity,which is helpful in solving specific cognition *** by this idea,we propose a directional connective network to achieve VCR by dynamically reorganizing the visual neuron connectivity that is contextualized using the meaning of questions and answers and leveraging the directional information to enhance the reasoning ***,we first develop a GraphVLAD module to capture visual neuron connectivity to fully model visual content ***,a contextualization process is proposed to fuse sentence representations with visual neuron ***,based on the output of contextualized connectivity,we propose directional connectivity to infer answers and rationales,which includes a ReasonVLAD *** results on the VCR dataset and visualization analysis demonstrate the effectiveness of our method.

关键词： Visual commonsense reasoning Directional connective network Visual neuron connectivity Contextualized connectivity Directional connectivity

来源：评论

学校读者我要写书评

暂无评论

The applied principles of EEG analysis methods in neuroscience and clinical neurology

引用

Military Medical Research 2024年第6期11卷 907-941页

作者： Hao Zhang Qing-Qi Zhou He Chen Xiao-Qing Hu Wei-Guang Li Yang Bai Jun-Xia Han Yao Wang Zhen-Hu Liang Dan Chen Feng-Yu Cong Jia-Qing Yan Xiao-Li Li School of Systems Science Beijing Normal UniversityBeijing 100875China College of Electrical and Control Engineering North China University of TechnologyBeijing 100041China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Department of Psychology the State Key Laboratory of Brain and Cognitive Sciencesthe University of Hong KongHong Kong SAR 999077China HKU-Shenzhen Institute of Research and Innovation Shenzhen 518057GuangdongChina Department of Health Technology and Informatics the Hong Kong Polytechnic UniversityHong Kong SAR 999077China Department of Rehabilitation Medicine the First Afliated Hospital of Nanchang UniversityNanchang 330006China Rehabilitation Medicine Clinical Research Center of Jiangxi Province Nanchang 330006China Beijing Key Laboratory of Learning and Cognition School of PsychologyCapital Normal UniversityBeijing 100048China School of Communication Science Beijing Language and Culture UniversityBeijing 100083China Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004HebeiChina School of Computer Science Wuhan UniversityWuhan 430072China School of Biomedical Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalian 116081LiaoningChina Guangdong Artifcial Intelligence and Digital Economy Laboratory(Guangzhou) Guangzhou 510335China.

Electroencephalography(EEG)is a non-invasive measurement method for brain *** to its safety,high resolution,and hypersensitivity to dynamic changes in brain neural signals,EEG has aroused much interest in scientific research and medical *** article reviews the types of EEG signals,multiple EEG signal analysis methods,and the application of relevant methods in the neuroscience feld and for diagnosing neurological ***,3 types of EEG signals,including time-invariant EEG,accurate event-related EEG,and random event-related EEG,are ***,5 main directions for the methods of EEG analysis,including power spectrum analysis,time-frequency analysis,connectivity analysis,source localization methods,and machine learning methods,are described in the main section,along with diferent sub-methods and effect evaluations for solving the same ***,the application scenarios of different EEG analysis methods are emphasized,and the advantages and disadvantages of similar methods are *** article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives,provide references for subsequent research,and summarize current issues and prospects for the future.

关键词： Electroencephalogram analysis methods Applied principles Neuroscience Diagnosis Neurological diseases

来源：评论

学校读者我要写书评

暂无评论

Chalcogenide Integrated Nanophotonics and Its Potential for Quantum Photonics

Chalcogenide Integrated Nanophotonics and Its Potential for ...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Kunhao Lei Kai Xu Kangjian Bao Jiawei Weng Lan Li Hongtao Lin The State Key Lab of Brain-Machine Intelligence Key Laboratory of Micro-Nano Electronics and Smart System of Zhejiang Province College of Information Science and Electronic Engineering Zhejiang University Hangzhou China The Key Laboratory of 3D Micro/ Nano Fabrication and Characterization of Zhejiang Province School of Engineering Westlake University Hangzhou Zhejiang China Institute of Advanced Technology Westlake Institute for Advanced Study Hangzhou Zhejiang China

Due to the high optical nonlinearity and nonvolatile phase-changing properties, chalcogenide integrated nanophotonics are emerging for entangling photon generation and nonvolatile quantum states operation. We will rev... 详细信息

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

关键词： Integrated optics Chalcogenides Nanophotonics Reviews Optical device fabrication Optical resonators Quantum state Optical network units Optical materials Quantum networks

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：