检索结果-内蒙古大学图书馆

FPGA-Based Convolution Accelerator and Memristor IP Core for Cooperative Acceleration of the YOLO Network 4

FPGA-Based Convolution Accelerator and Memristor IP Core for...

4th International Conference on Computer Science, Electronic Information engineering and Intelligent Control technology, CEI 2024

作者： Tan, Aolong Yang, Yucheng Duan, Shukai Wang, Lidan College of Artificial Intelligence Southwest University Chongqing400715 China State Key Laboratory of Intelligent Vehicle Safety Technology China National Local Joint Engineering Research Center of Intelligent Transmission and Control Technology 400715 China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing400715 China Laboratory of Luminescence Analysis and Molecular Sensing Southwest University Ministry of Education Chongqing400715 China

ISBN: (纸本)9798350378542

Object detection technology is widely used in areas such as autonomous driving, drone reconnaissance, smart surveillance and industrial automation, especially in remote or hazardous scenarios where it can improve efficiency and safety. Therefore, the development of a high-precision, low-power acceleration system integrated with low-power hardware is crucial. This paper proposes a collaborative acceleration scheme for the YOLO network based on an FPGA convolution accelerator and simulated memristors, which successfully implements and accelerates the YOLOv4-Tiny model. First, a reconfigurable single-core accelerator operator is designed for various computational operations in the model. Second, taking advantage of the digital device characteristics of memristors and the hardware resources of the FPGA, a memristor simulation IP core is built to exploit its memory characteristics for convolution operations. Through the synergistic effect of the convolution accelerator and the simulated IP core, a hybrid acceleration of the detection model is achieved. The power consumption of the convolution accelerator is only 2.75W, and in testing, the detection time for a single image is 823ms with an average accuracy of over 0.95, achieving high detection performance. This provides an opportunity to explore and research the efficient acceleration of object detection networks with integrated storage and computation. © 2024 IEEE.

关键词： Reconfigurable hardware

来源：评论

学校读者我要写书评

暂无评论

AFNet-M: Adaptive Fusion Network with Masks for 2D+3D Facial Expression Recognition

arXiv

引用

arXiv 2022年

作者： Sui, Mingzhe Li, Hanting Zhu, Zhaoqing Zhao, Feng The Department of Automation School of Information Science and Technology University of Science and Technology of China Hefei230027 China The National Engineering Laboratory for Brain-inspired Intelligence Hefei230027 China

2D+3D facial expression recognition (FER) can effectively cope with illumination changes and pose variations by simultaneously merging 2D texture and more robust 3D depth information. Most deep learning-based approaches employ the simple fusion strategy that concatenates the multimodal features directly after fully-connected layers, without considering the different degrees of significance for each modality. Meanwhile, how to focus on both 2D and 3D local features in salient regions is still a great challenge. In this letter, we propose the adaptive fusion network with masks (AFNet-M) for 2D+3D FER. To enhance 2D and 3D local features, we take the masks annotating salient regions of the face as prior knowledge and design the mask attention module (MA) which can automatically learn two modulation vectors to adjust the feature maps. Moreover, we introduce a novel fusion strategy that can perform adaptive fusion at convolutional layers through the designed importance weights computing module (IWC). Experimental results demonstrate that our AFNet-M achieves the state-of-the-art performance on BU-3DFE and Bosphorus datasets and requires fewer parameters in comparison with other models. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Increased cysteinyl-tRNA synthetase drives neuroinflammation in Alzheimer’s disease

引用

Translational Neurodegeneration 2024年第1期13卷 1064-1082页

作者： Xiu-Hong Qi Peng Chen Yue-Ju Wang Zhe-Ping Zhou Xue-Chun Liu Hui Fang Chen-Wei Wang Ji Liu Rong-Yu Liu Han-Kui Liu Zhen-Xin Zhang Jiang-Ning Zhou Chinese Academy of Sciences Key Laboratory of Brain Function and Diseases Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230027China Institute of Brain Science The First Affiliated Hospital of Anhui Medical UniversityHefei 230022China Department of Geriatrics The First Affiliated Hospital of Soochow UniversitySuzhou 215006China Department of Neurology Hefei Hospital Affiliated to Anhui Medical UniversityHefei 230011China Anhui Institute of Pediatric Research Anhui Provincial Children’s HospitalHefei 230051China School of Basic Medical Sciences Anhui Medical UniversityHefei 230032China National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application School of Information Science and Technologyand The First Affiliated Hospital of USTCDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230027China Department of Respiratory and Critical Care The First Affiliated Hospital of Anhui Medical UniversityHefei 230022China Key Laboratory of Diseases and Genomes BGI-GenomicsBGI-ShenzhenShenzhen 518000China Department of Neurology and Clinical Epidemiology Unit Peking Union Medical College HospitalChinese Academy of Medical SciencesBeijing 100007China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China

Background Microglia-mediated neuroinflammation in Alzheimer’s disease(AD)is not only a response to pathophysiological events,but also plays a causative role in *** cysteinyl-tRNA synthetase(CARS)is considered to be a stimulant for immune responses to diseases;however,it remains unknown whether CARS is involved in the pathogenesis of *** Postmortem human temporal cortical tissues at different Braak stages and AD patient-derived serum samples were used to investigate the changes of CARS levels in AD by immunocytochemical staining,real-time PCR,western blotting and *** that,C57BL/6J and APP/PS1 transgenic mice and BV-2 cell line were used to explore the role of CARS protein in memory and neuroinflammation,as well as the underlying ***,the associations of morphological features among CARS protein,microglia and dense-core plaques were examined by immu-nocytochemical *** A positive correlation was found between aging and the intensity of CARS immunoreactivity in the temporal *** protein and mRNA levels of CARS were increased in the temporal cortex of AD *** staining revealed increased CARS immunoreactivity in neurons of the temporal cortex in AD ***,overexpression of CARS in hippocampal neurons induced and aggravated cognitive dysfunction in C57BL/6J and APP/PS1 mice,respectively,accompanied by activation of microglia and the TLR2/MyD88 signaling pathway as well as upregulation of proinflammatory *** vitro experiments showed that CARS treatment facilitated the production of proinflammatory cytokines and the activation of the TLR2/MyD88 signaling pathway of BV-2 *** accumulation of CARS protein occurred within dense-core Aβplaques accompanied by recruitment of ameboid *** upregulation of TLR2/MyD88 proteins was also observed in the temporal cortex of *** The findings suggest that the neuronal CARS drives neuroinflam

关键词： Cysteinyl-tRNA synthetase Alzheimer’s disease Neuroinflammation Microglia TLR2

来源：评论

学校读者我要写书评

暂无评论

DENOISED INTERNAL MODELS: A brain-inspired AUTOENCODER AGAINST ADVERSARIAL ATTACKS

arXiv

引用

arXiv 2021年

作者： Liu, Kaiyuan Li, Xingyu Lai, Yurui Zhang, Ge Su, Hang Wang, Jiachen Guo, Chunxu Xie, Hong Guan, Ji-Song Zhou, Yi School of Life Sciences and Technology ShanghaiTech University China Shanghai Center for Brain Science and Brain-Inspired Technology China School of Life Sciences Tsinghua University China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application School of Information Science and Technology University of Science and Technology of China China Institute of Photonic Chips University of Shanghai for Science and Technology China Centre for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology China

Despite its great success, deep learning severely suffers from robustness;that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. inspired from the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised deep generative modelling of incomplete multi-modality emotional data

arXiv

引用

arXiv 2018年

作者： Du, Changde Du, Changying Wang, Hao Li, Jinpeng Zheng, Wei-Long Lu, Bao-Liang He, Huiguang Research Center for Brain-inspired Intelligence National Laboratory of Pattern Recognition CASIA University of CAS Beijing China 360 Search Lab Beijing China Department of Computer Science and Engineering SJTU Shanghai China Research Center for Brain-inspired Intelligence National Laboratory of Pattern Recognition CASIA Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences University of Chinese Academy of Sciences

There are threefold challenges in emotion recognition. First, it is difficult to recognize human’s emotional states only considering a single modality. Second, it is expensive to manually annotate the emotional data. Third, emotional data often suffers from missing modalities due to unforeseeable sensor malfunction or configuration issues. In this paper, we address all these problems under a novel multi-view deep generative framework. Specifically, we propose to model the statistical relationships of multi-modality emotional data using multiple modality-specific generative networks with a shared latent space. By imposing a Gaussian mixture assumption on the posterior approximation of the shared latent variables, our framework can learn the joint deep representation from multiple modalities and evaluate the importance of each modality simultaneously. To solve the labeled-data-scarcity problem, we extend our multi-view model to semi-supervised learning scenario by casting the semi-supervised classification problem as a specialized missing data imputation task. To address the missing-modality problem, we further extend our semi-supervised multi-view model to deal with incomplete data, where a missing view is treated as a latent variable and integrated out during inference. This way, the proposed overall framework can utilize all available (both labeled and unlabeled, as well as both complete and incomplete) data to improve its generalization ability. The experiments conducted on two real multi-modal emotion datasets demonstrated the superiority of our framework. Copyright © 2018, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Boosting Multi-modal Model Performance with Adaptive Gradient Modulation

arXiv

引用

arXiv 2023年

作者： Li, Hong Li, Xingyu Hu, Pengbo Lei, Yinuo Li, Chunxiao Zhou, Yi School of Information Science and Technology ShanghaiTech University China Shanghai Innovation Center for Processor Technologies China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai China School of Information Science and Technology University of Science and Technology of China Hefei China School of Management University of Science and Technology of China Hefei China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application University of Science and Technology of China Hefei China Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China Ministry of Education China

While the field of multi-modal learning keeps growing fast, the deficiency of the standard joint training paradigm has become clear through recent studies. They attribute the sub-optimal performance of the jointly trained model to the modality competition phenomenon. Existing works attempt to improve the jointly trained model by modulating the training process. Despite their effectiveness, those methods can only apply to late fusion models. More importantly, the mechanism of the modality competition remains unexplored. In this paper, we first propose an adaptive gradient modulation method that can boost the performance of multi-modal models with various fusion strategies. Extensive experiments show that our method surpasses all existing modulation methods. Furthermore, to have a quantitative understanding of the modality competition and the mechanism behind the effectiveness of our modulation method, we introduce a novel metric to measure the competition strength. This metric is built on the mono-modal concept, a function that is designed to represent the competition-less state of a modality. Through systematic investigation, our results confirm the intuition that the modulation encourages the model to rely on the more informative modality. In addition, we find that the jointly trained model typically has a preferred modality on which the competition is weaker than other modalities. However, this preferred modality need not dominate others. Our code will be available at https://github. com/lihong2303/AGM_ICCV2023. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MXene-Enhanced Hydrogel Cardiac Patch with High Electrical Conductivity, Mechanical Strength, and Excellent Biocompatibility

SSRN

引用

SSRN 2025年

作者： Wang, Fei Liang, Fuying Chen, Qi Huang, Jingcheng Wang, Xi Cheng, Wei Cui, Jizhai Xu, Fan Mei, Yongfeng Wu, Xiaojun Song, Enming Shanghai Frontiers Science Research Base of Intelligent Optoelectronics and Perception Institute of Optoelectronics Fudan University Shanghai200438 China National University of Singapore Singapore117575 Singapore Department of Materials Science Institute of Optoelectronics Fudan University Shanghai200438 China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China International Institute of Intelligent Nanorobots and Nanosystems Fudan University Shanghai200438 China Yiwu Research Institute of Fudan University Zhejiang Yiwu322000 China Institute of Mechanics and Computational Engineering Department of Aeronautics and Astronautics Fudan University 220 Handan Road Shanghai200433 China State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Fudan University China

Myocardial infarction (MI), a leading cause of death, triggers cardiomyocyte death and scar tissue formation, disrupting electrical conduction and impairing cardiac function, which may ultimately progress to heart failure. In this study, we developed a high-conductivity and high-toughness hydrogel cardiac patch (MPPH) by incorporating MXene nanosheets into a PVA/PAM hydrogel. MPPH showed superior mechanical properties, with tensile strength of 190 kPa and elongation over 1250%. MXene enhanced the electrical conductivity of MPPH, benefiting the restoration of conduction in infarcted areas. Additionally, MPPH exhibited strong adhesion to muscle and skin tissues, with the maximum adhesion strength reaching 15 kPa. Biocompatibility tests revealed that MPPH has high cell viability. These findings indicate that MPPH is a promising material for cardiac functional repair and MI treatment. © 2025, The Authors. All rights reserved.

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

Cross-dimension Affinity Distillation for 3D EM Neuron Segmentation

Cross-dimension Affinity Distillation for 3D EM Neuron Segme...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaoyu Liu Miaomiao Cai Yinda Chen Yueyi Zhang Te Shi Ruobing Zhang Xuejin Chen Zhiwei Xiong MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Sciences

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Accurate 3D neuron segmentation from electron mi-croscopy (EM) volumes is crucial for neuroscience re-search. However, the complex neuron morphology often leads to over-merge and over-segmentation results. Recent advancements utilize 3D CNNs to predict a 3D affinity map with improved accuracy but suffer from two challenges: high computational cost and limited input size, especially for practical deployment for large-scale EM volumes. To address these challenges, we propose a novel method to leverage lightweight 2D CNNs for efficient neuron segmen-tation. Our method employs a 2D Y-shape network to generate two embedding maps from adjacent 2D sections, which are then converted into an affinity map by measuring their embedding distance. While the 2D network better captures pixel dependencies inside sections with larger in-put sizes, it overlooks inter-section dependencies. To over-come this, we introduce a cross-dimension affinity distillation (CAD) strategy that transfers inter-section dependency knowledge from a 3D teacher network to the 2D student network by ensuring consistency between their output affin-ity maps. Additionally, we design a feature grafting in-teraction (FGI) module to enhance knowledge transfer by grafting embedding maps from the 2D student onto those from the 3D teacher. Extensive experiments on multiple EM neuron segmentation datasets, including a newly built one by ourselves, demonstrate that our method achieves supe-rior performance over state-of-the-art methods with only 1/20 inference latency. We release our code and dataset at https://***/liuxyll03/CAD.

关键词： Knowledge engineering Solid modeling Three-dimensional displays Accuracy Neuroscience Neurons Morphology

来源：评论

学校读者我要写书评

暂无评论

Learning Large-Factor EM Image Super-Resolution with Generative Priors

Learning Large-Factor EM Image Super-Resolution with Generat...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiateng Shou Zeyu Xiao Shiyu Deng Wei Huang Peiyao Shi Ruobing Zhang Zhiwei Xiong Feng Wu MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Sciences Institute of Artificial Intelligence Hefei Comprehensive National Science Center

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

As the mainstream technique for capturing images of biological specimens at nanometer resolution, electron microscopy (EM) is extremely time-consuming for scanning wide field-of-view (FOV) specimens. In this paper, we investigate a challenging task of large-factor EM image super-resolution (EMSR), which holds great promise for reducing scanning time, relaxing acquisition conditions, and expanding imaging FOV. By exploiting the repetitive structures and volumetric coherence of EM images, we propose the first generative learning-based framework for large-factor EMSR. Specifically, motivated by the predictability ofrepetitive structures and textures in EM images, we first learn a discrete codebook in the latent space to represent highresolution (HR) cell-specific priors and a latent vector indexer to map low-resolution (LR) EM images to their corresponding latent vectors in a generative manner. By incorporating the generative cell-specific priors from HR EM images through a multi-scale prior fusion module, we then deploy multi-image feature alignment and fusion to further exploit the inter-section coherence in the volumetric EM data. Extensive experiments demonstrate that our proposed framework outperforms advanced single-image and video super-resolution methods for 8× and 16× EMSR (i.e., with 64 times and 256 times less data acquired, respectively), achieving superior visual reconstruction quality and down-stream segmentation accuracy on benchmark EM datasets. Code is available at https://***/jtshou/GPEMSR.

关键词： Image segmentation Visualization Scanning electron microscopy Accuracy Superresolution Coherence Vectors

来源：评论

学校读者我要写书评

暂无评论

Automatic Construction of Parallel Algorithm Portfolios for Multi-objective Optimization

arXiv

引用

arXiv 2022年

作者： Ma, Xiasheng Liu, Shengcai Hong, Wenjing School of Mechanical Engineering University of Science and Technology Beijing Beijing100083 China Beijing Key Laboratory of Research and Application for Robotic Intelligence of Hand-Eye-Brain Interaction Beijing100083 China Singapore Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

It has been widely observed that there exists no universal best Multi-objective Evolutionary Algorithm (MOEA) dominating all other MOEAs on all possible Multi-objective Optimization Problems (MOPs). In this work, we advocate using the Parallel Algorithm Portfolio (PAP), which runs multiple MOEAs independently in parallel and gets the best out of them, to combine the advantages of different MOEAs. Since the manual construction of PAPs is non-trivial and tedious, we propose to automatically construct high-performance PAPs for solving MOPs. Specifically, we first propose a variant of PAPs, namely MOEAs/PAP, which can better determine the output solution set for MOPs than conventional PAPs. Then, we present an automatic construction approach for MOEAs/PAP with a novel performance metric for evaluating the performance of MOEAs across multiple MOPs. Finally, we use the proposed approach to construct a MOEAs/PAP based on a training set of MOPs and an algorithm configuration space defined by several variants of NSGA-II. Experimental results show that the automatically constructed MOEAs/PAP can even rival the state-of-the-art ensemble MOEAs designed by human experts, demonstrating the huge potential of automatic construction of PAPs in multi-objective optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Parallel 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：