检索结果-内蒙古大学图书馆

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Xu, Xintao Jiang, Zhelong Chen, Gang Li, Zhigang Gong, Guoliang Lu, Huaxiang University of Science and Technology of China School of Microelectronics Hefei China Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Materials and Optoelectronics Research Center Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China

ISBN: (纸本)9781665459112

This paper proposes a generic neural network fitting algorithm based on CNN for nonlinear functions that overcomes the challenges of a large number of nonlinear functions in terms of hardware deployment and computing circuit generality in diverse neural network models. The model takes advantage of the principle that functions have varying degrees of difficulty fitting in different spaces, mapping the input to high-dimensional space with 1x1 convolution, and utilizing CNN to extract features of nonlinear functions with its strong feature extraction ability in high-dimensional space. Furthermore, MaxPool and ReLU improve the ability of nonlinear fitting. When fitting Tanh, Sigmoid, and ELU activation functions with 16bit accuracy, the proposed algorithm has an average error of less than 0.0006, with a parameter size of 5.793 k. © 2022 IEEE.

关键词： Functions

来源：评论

学校读者我要写书评

暂无评论

SSCGAN: Speech style conversion based on GAN

SSCGAN: Speech style conversion based on GAN

引用

2022 International Conference on Algorithms, Microchips and Network Applications

作者： Li, Jixing Guo, Xiaozhou Shen, Ronxuan Lu, Huaxiang Wang, Xinggang Cao, Zhanzhong Zhang, Chi Mao, Wenyu Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing100083 China College of Microelectronics University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing100083 China Nanjing Research Institute of Information Technology Nanjing210009 China

ISBN: (纸本)9781510653290

Speech conversion has significant applications in medical, robotics, and other industries. With the rise of deep learning, CycleGAN is widely used in speech conversion technology. However, the existing CycleGAN-based methods do not consider the speech signal's temporal and spatial features. In addition, the training of CycleGAN is difficult to converge due to the gradient disappearance problem of the generator. We propose SSCGAN, whose generator is a U-shaped encoder-decoder network that extracts the temporal and spatial features by using 1DCNN and 2DCNN in parallel. A feature fusion module based on multi-scale mixed convolution is embedded between encoder and decoder to achieve high-level fusion of spatial features and temporal features. To make the network training more stable and easier to converge, SSCGAN uses Wasserstein distance instead of the original Jensen-Shannon divergence to calculate the distance of the probability distribution, which can alleviate the gradient extinction problem for generators. In addition, SSCGAN utilizes the PatchGAN structure in the discriminator, which considers the samples' local details by dividing them into different patches. It can improve the discriminative ability of SSCGAN. The experiment results in the nonparallel corpus database VCC 2018 show that SSCGAN is superior to existing methods such as CycleGAN-VC, StarGan-VC. In inter-gender speech conversion, the MSD of SSCGAN is decreased by 0.162 on average compared to other methods, and in intra-gender speech conversion, the MSD is decreased by 0.118 on average. In subjective evaluation, participants also think SSCGAN is the best. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Rescon-Net: Transfer Learning Based Nested Model for Cerebrovascular Segmentation with Aneurysm

Rescon-Net: Transfer Learning Based Nested Model for Cerebro...

引用

IEEE International Symposium on Biomedical Imaging

作者： Chaoran Zhang Ming Zhao Yixuan Xie Ming Ma Kaiwen Guo Rui Ding Hongzhen Jiang Wei Xi Likun Xia Laboratory of Neural Computing and Intelligent Perception (NCIP) Capital Normal University Beijing China Department of Neurosurgery First Medical Center Chinese PLA General Hospital Beijing China Department of Computer Science Winona State University Winona MN USA Department of Radiology Fourth Medical Center Chinese PLA General Hospital Beijing China

In the field of cerebral vascular segmentation, existing models have achieved excellent results in normal subjects. However, such models may not be satisfactory in cerebral vessels with aneurysms or malformation in emergency cases, particularly, when the vessels are small, thus resulting in poor segmentation results. We propose a transfer learning strategy based pre-trained model termed ReSCon-Net, using publicly available dataset for cerebrovascular segmentation with aneurysms or malformation in emergency cases. In details, the transfer learning strategy takes advantage of pre-trained models using a large volume of dataset from normal subjects and provides a solution for relatively small clinical datasets of patients. This can be achieved by fine-tuning the parameters in the last layers of the proposed model termed ReSCon-Net, which consists of three blocks: ResMul, DeRes, and REAM. The first two blocks aim to address inadequate extraction of weak vessels by using different convolution sizes to achieve multiscale features; REAM block can enhance the vessel edges by obtaining the probability of a voxel weight corresponding to reverse.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point convolutional neural network algorithm for Ising model ground state research based on spring vibration

arXiv

引用

arXiv 2023年

作者： Jiang, Zhelong Chen, Gang Qiao, Ruixiu Feng, Pengcheng Chen, Yihao Su, Junjia Zhao, Zhiyuan Jin, Min Chen, Xu Li, Zhigang Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing China School of Microelectronics University of Science and Technology of China Hefei China College of Microelectronics University of Chinese Academy of Sciences Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China

The ground state search of the Ising model can be used to solve many combinatorial optimization problems. Under the current computer architecture, an Ising ground state search algorithm suitable for hardware computing is necessary for solving practical problems. Inspired by the potential energy conversion of springs, we propose a point convolutional neural network algorithm for ground state search based on spring vibration model, called Spring-Ising Algorithm. Spring-Ising Algorithm regards the spin as a moving mass point connected to a spring and establish the equation of motion for all spins. Spring-Ising Algorithm can be mapped on the GPU or AI chips through the basic structure of the neural network for fast and efficient parallel computing. The algorithm has very productive results for solving the Ising model and has been test in the recognized test benchmark K2000. The algorithm introduces the concept of dynamic equilibrium to achieve a more detailed local search by dynamically adjusting the weight of the Ising model in the spring oscillation model. Finally, there is the simple hardware test speed evaluation. Spring-Ising Algorithm can provide the possibility to calculate the Ising model on a chip which focuses on accelerating neural network calculations. © 2023, CC BY.

关键词： Equations of motion

来源：评论

学校读者我要写书评

暂无评论

An FPGA-Based High-Throughput Dataflow Accelerator for Lightweight neural Network

An FPGA-Based High-Throughput Dataflow Accelerator for Light...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhiyuan Zhao Jixing Li Gang Chen Zhelong Jiang Ruixiu Qiao Peng Xu Yihao Chen Huaxiang Lu School of Microelectronics University of Science and Technology of China Hefei China Institute of Semiconductors Chinese Academy of Sciences Beijing China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing China College of Microelectronics University of Chinese Academy of Sciences Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Lightweight neural networks (LWNNs) have drawn significant attention recently for compact architecture and acceptable accuracy. Despite achieving substantial reductions in computation complexity and model size, increased memory access demands are caused by the extensive use of depthwise separable convolutions (DSCs) and skip-connection blocks (SCBs), which makes it difficult to achieve the anticipated performance. To process LWNNs efficiently, an FPGA-based dataflow accelerator is proposed in this paper. Firstly, a pixel-based streaming strategy is introduced to reduce off-chip memory access while minimizing on-chip memory overhead. Furthermore, an adaptive bandwidth computing engine (CE) is designed to increase computational efficiency in multi-CE architecture. Finally, based on the scalable CE, a dynamic parallelism allocation algorithm is proposed to avoid underutilization of on-chip computing resources. Shuf-fleNetV2 is implemented on Xilinx ZC706 platform, and the results show the proposed accelerator can achieve a state-of-the-art performance of 1771.2 FPS and computational efficiency of 0.64 GOPS/DSP, which is 5.3× of the reference design.

关键词： Performance evaluation Heuristic algorithms neural networks Bandwidth Computer architecture Parallel processing Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Cerebrovascular Segmentation in MRA via Reverse Edge Attention Network 23rd

Cerebrovascular Segmentation in MRA via Reverse Edge Attenti...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Zhang, Hao Xia, Likun Song, Ran Yang, Jianlong Hao, Huaying Liu, Jiang Zhao, Yitian College of Information Engineering Capital Normal University Beijing China Cixi Institute of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China School of Control Science and Engineering Shandong University Jinan China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China International Science and Technology Cooperation Base of Electronic System Reliability and Mathematical Interdisciplinary Capital Normal University Beijing China Laboratory of Neural Computing and Intelligent Perception Capital Normal University Beijing China Beijing Advanced Innovation Center for Imaging Theory and Technology Capital Normal University Beijing China

ISBN: (纸本)9783030597245

Automated extraction of cerebrovascular is of great importance in understanding the mechanism, diagnosis, and treatment of many cerebrovascular pathologies. However, segmentation of cerebrovascular networks from magnetic resonance angiography (MRA) imagery continues to be challenging because of relatively poor contrast and inhomogeneous backgrounds, and the anatomical variations, complex geometry and topology of the networks themselves. In this paper, we present a novel cerebrovascular segmentation framework that consists of image enhancement and segmentation phases. We aim to remove redundant features, while retaining edge information in shallow features when combining these with deep features. We first employ a Retinex model, which is able to model noise explicitly to aid removal of imaging noise, as well as reducing redundancy within an image and emphasizing the vessel regions, thereby simplifying the subsequent segmentation problem. Subsequently, a reverse edge attention module is employed to discover edge information by paying particular attention to the regions that are not salient in high-level semantic features. The experimental results show that the proposed framework enables the reverse edge attention network to deliver a reliable cerebrovascular segmentation. © 2020, Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Acq: Improving Generative Data-Free Quantization Via Attention Correction

SSRN

引用

SSRN 2023年

作者： Li, Jixing Guo, Xiaozhou Dai, Benzhe Gong, Guoliang Jin, Min Chen, Gang Mao, Wenyu Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing100083 China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing100083 China College of Microelectronics University of Chinese Academy of Sciences Beijing China

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a generator is a popular data-free quantization method, which is called generative data-free quantization. However, there is a difference in attention between synthetic samples and authentic samples. This is always ignored and restricts the quantization performance. First, since synthetic samples of the same class are prone to have homogenous attention, the quantized network can only learn limited modes of attention. Second, synthetic samples in eval mode and training mode exhibit different attention. Hence, the batch-normalization statistics matching tends to be inaccurate. ACQ is proposed in this paper to fix the attention of synthetic samples. An attention center position-condition generator is established regarding the homogenization of intra-class attention. Restricted by the attention center matching loss, the attention center position is treated as the generator’s condition input to guide synthetic samples in obtaining diverse attention. Moreover, we design adversarial loss of paired synthetic samples under the same condition to prevent the generator from paying overmuch attention to the condition, which may result in mode collapse. To improve the attention similarity of synthetic samples in different network modes, we introduce a consistency penalty to guarantee accurate BN statistics matching. The experimental results demonstrate that ACQ effectively improves the attention problems of synthetic samples. Under various training settings, ACQ achieves the best quantization performance. For the 4-bit quantization of Resnet18 and Resnet50, ACQ reaches 67.55% and 72.23% accuracy, respectively. © 2023, The Authors. All rights reserved.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

ACQ: Improving Generative Data-free Quantization Via Attention Correction

arXiv

引用

arXiv 2023年

作者： Li, Jixing Guo, Xiaozhou Dai, Benzhe Gong, Guoliang Jin, Min Chen, Gang Mao, Wenyu Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100049 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing100083 China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing100049 China College of Microelectronics University of Chinese Academy of Sciences Beijing100049 China

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a generator is a popular data-free quantization method, which is called generative data-free quantization. However, there is a difference in attention between synthetic samples and authentic samples. This is always ignored and restricts the quantization performance. First, since synthetic samples of the same class are prone to have homogenous attention, the quantized network can only learn limited modes of attention. Second, synthetic samples in eval mode and training mode exhibit different attention. Hence, the batch-normalization statistics matching tends to be inaccurate. ACQ is proposed in this paper to fix the attention of synthetic samples. An attention center position-condition generator is established regarding the homogenization of intra-class attention. Restricted by the attention center matching loss, the attention center position is treated as the generator's condition input to guide synthetic samples in obtaining diverse attention. Moreover, we design adversarial loss of paired synthetic samples under the same condition to prevent the generator from paying overmuch attention to the condition, which may result in mode collapse. To improve the attention similarity of synthetic samples in different network modes, we introduce a consistency penalty to guarantee accurate BN statistics matching. The experimental results demonstrate that ACQ effectively improves the attention problems of synthetic samples. Under various training settings, ACQ achieves the best quantization performance. For the 4-bit quantization of Resnet18 and Resnet50, ACQ reaches 67.55% and 72.23% accuracy, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Comparison of seven approaches for holter ECG clustering and classification

Comparison of seven approaches for holter ECG clustering and...

引用

29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS 2007), vol.10

作者： Vaclav Chudacek Milan Petrik George Georgoulas Miroslav Cepek Lenka Lhotska Chrysostomos Stylios Gerstner laboratory at Department of Cybernetics Czech Technical University Czech Republic Czech Republic Department of Cybernetics Center for Machine Perception Czech Technical University Czech Republic Intelligent Control Systems Laboratory Georgia Technology Research Institute Atlanta USA Czech Republic Department of Computer Science and Engineering Neural Computing Group Czech Technical University Czech Republic Czech Republic Department of Cybernetics Gerstner Laboratory Czech Technical University Czech Republic Department of Informatics and Communications Technology TEI Epirus Artas Greece

In this work we present a comparative study, testing selected methods for clustering and classification of holter electrocardiogram (ECG). More specifically we focus on the task of discriminating between normal 'N' beats and premature ventricular 'V' beats. Some of the tested methods represent the state of the art in pattern analysis, while others are novel algorithms developed by us. All the algorithms were tested on the same datasets, namely the MIT-BIH and the AHA databases. The results for all the employed methods are compared and evaluated using the measures of sensitivity and specificity.

关键词： Electrocardiography Testing Decision trees Laboratories Cybernetics Sensitivity and specificity Heart rate variability Clustering algorithms Spatial databases Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Fault Detection Method for Tree Contact Single-Phase-To-Ground Fault

SSRN

引用

SSRN 2023年

作者： Wu, Juping Xv, Huikai Jin, Min Gong, Guoliang Chen, Gang Mao, Wenyu Lu, Huaxiang Chen, Tianxiang Institute of Semiconductors CAS Beijing100083 China University of Chinese Academy of Sciences Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China Collage of Microelectronics University of Chinese Academy of Sciences Beijing China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing China Tianjin University of Science and Technology Tianjin300457 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China

High impedance fault(HIF), especially tree contact single-phase-to-ground fault(TSF), often occurs in resonant grounding systems and are difficult to detect. Therefore, there is an urgent need for an effective TSF detection technology. In this paper, by analyzing the equivalent circuits of different impedance faults in resonant grounding system, and analyzing the transient zero-sequence components of underdamped state and overdamped state under different impedance, the conclusion is drawn: When a TSF occurs, the transient zero-sequence voltage will have a unique " Beat frequency " characteristic, and the problem of covering this phenomenon due to the imbalance of distribution network is effectively solved by fast independent component analysis(FastICA). Based on this conclusion, A fault detection method for TSF based on FastICA is proposed. Finally, the study conducted real experiments using two different impedance trees, bamboo and pine, to verify the proposed detection method. The results of the experiment found clear support for that the detection method is accurate and effective. © 2023, The Authors. All rights reserved.

关键词： Fault detection

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：