检索结果-内蒙古大学图书馆

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Lu Luo Shukai Duan Lidan Wang College of Electronic and Information Engineering Southwest University Chongqing China Brain-inspired Computing & Intelligent Control of Chongqing Key Lab National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing Brain Science Collaborative Innovation Center College of Artificial Intelligence Southwest University Chongqing China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Convolutional neural networks (CNNs) have achieved the best performance in some fields. However, they still have some defects. CNNs need a lot of images for training; they will lose much information in the pooling layer, which reduces the spatial resolution. Facing such problems, Hinton et al. proposed a capsule network (CapsNet). Although the CapsNet has achieved the best accuracy on MNIST dataset, it has not performed well on Fashion-MNIST, Cifar-10 and other datasets. Naturally, we established an improved version of capsule network (R-CapsNet). Results have shown that when using R-CapsNet model, the loss gets decreased and the accuracy gets improved on FashionMNIST. In the meanwhile, the training parameters are reduced by nearly half. Specifically, it reduces by 4.5M. Comparisons show that our proposed model reports improved accuracy of around 0.56% over the existing state-of-the-art systems in literature. The test accuracy of R-CapsNet model is 1.32% higher than that of the original model. Furthermore, better results have been achieved on Cifar-10 with R-CapsNet model and it has easily increased by 10% compared to CapsNet.

关键词： Convolution Kernel Training Feature extraction Image recognition Image reconstruction Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Global Self-Attention Memristive Neural Network for Image Restoration

SSRN

引用

SSRN 2023年

作者： Zhang, Wenhao Xiao, He Xie, Dirui Zhou, Yue Duan, Shukai Hu, Xiaofang College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Chongqing400715 China Key Laboratory of Luminescence Analysis and Molecular Sensing Southwest University Ministry of Education China

Convolutional neural networks(CNNs) are widely used in image restoration tasks, but they are limited by local operations and cannot be used to model long-range pixel dependencies. Recently, using the idea of non-local operations, various non-local networks and the Vision Transformer have been proposed to address this problem of CNNs. However, most of these models cannot adaptively process images with different resolutions, and their large number of parameters and computational complexity make them unfavorable for edge deployment. In this paper, we propose an efficient Global Self-Attention Memristive Neural Network (GSA-MNN) for image restoration and present a circuit implementation scheme for GSA-MNN based on memristors. GSA-MNN can both extract global and local information from images and has fully convolutional properties, which can be flexibly applied to different resolution images. Specifically, we design two global attention modules: The Global Spatial Attention Module (GSAM) and the Global Channel Attention Module (GCAM) to complete the modeling and inference of global relations. The GSAM is used to model global spatial relations between the pixels of the feature maps, while the GCAM explores global relations across the channels. In order to deal with image regions with complex textures, we also designed a multi-scale local information extraction module. Powered by these three modules, GSA-MNN enjoys an excellent ability to capture both global and local dependencies in image restoration. Finally, we provide a full-circuit implementation scheme for these three modules, using a modular design to complete the circuit design of the entire GSA-MNN. Benefiting from the programmability of the memristor crossbar, three kinds of image restoration tasks: image deraining, low-light image enhancement, and image dehazing are realized on the same circuit framework by adjusting the configuration parameters. Experimental comparisons with over 20 state-of-the-art methods on 1

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Few-Shot Problem of Gas Concentration Prediction Based on Wavelet Kernel-Based Broad Learning System

SSRN

引用

SSRN 2024年

作者： Zhao, Wenlong Ma, Ruilong Yan, Jia Duan, Shukai Peng, Xiaoyan Chu, Jin College of Artificial Intelligence Southwest University Chongqing400715 China Chongqing Key Laboratory of Brain-Inspired Computing and Intelligent Chips Chongqing400715 China Key Laboratory of Luminescence Analysis and Molecular Sensing Ministry of Education Chongqing400715 China

Gas concentrations vary over a wide range, making it impractical to repeatedly collect large numbers of samples at the same concentration levels, which results in sample scarcity. To solve the few-sample problem in gas concentration prediction, a wavelet kernel-based BLS (WKBLS) method is proposed in this paper to replace the feature layer and enhancement layer of the original BLS with wavelet sequence and kernel matrix, respectively, which effectively alleviates the uncertainty of double random mapping and emphasizes the intra-sample and inter-sample relationships. The downsampled data from a public dataset is applied to the WKBLS and other existing deep neural networks and machine learning methods. Furthermore, a highly sensitive HCHO gas sensor based on SnO2 is integrated with commercial sensors to form an array for HCHO data acquisition. Experimental results confirm that WKBLS effectively addresses the few-shot problem and demonstrates strong generalization in low-frequency and time-series data. © 2024, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

High-Performance Convolutional Neural Network Emulation Via Fpga-Integrated Memristive Circuitry

SSRN

引用

SSRN 2024年

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

In this study, to tackle the challenges of high cost, insufficient reliability, and short lifespan associated with physical memristors, a FPGA-based memristor simulation circuit is proposed. This circuit is deployed on the Xilinx ZYNQ-7000 FPGA XC7Z020, with a resource utilization rate of less than 1%, and has been successfully integrated and validated. Moreover, the paper leverages a memristor model to build a convolutional neural network for MNIST image recognition, which achieves an accuracy of 90.22% with a parameter count of 512. © 2024, The Authors. All rights reserved.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Optimization of Stacked Chip Macro-Module Layout Based on Memristor-inspired Evolutionary Game

Multi-Modal Optimization of Stacked Chip Macro-Module Layout...

引用

Electronic Information Engineering and Computer Communication (EIECC), International Conference on

作者： Kaikai Qiao Ben Ma Mingze Chen Ke Ding Changqing Li Shukai Duan Lidan Wang State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China College of Artificial Intelligence Southwest University Chongqing China National & Local Joint Engineering Research Center of of Intelligent Transmission and Control Technology Chongqing China Chongqing Key Laboratory of Brain-Inspired Computing and Intelligent Chips Chongqing China Key Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University) Ministry of Education Chongqing China

ISBN: (数字)9798331534622

ISBN: (纸本)9798331534639

As the complexity of chip design continues to increase, the stacking of multiple device layers in a three dimension(3D) architecture has emerged as a promising approach, which aims to optimize the placement and interconnections of large function blocks across the vertically-stacked device layers. Due to the complex interactions between layout and design constraints, traditional deterministic optimization often struggle to navigate its multi-modal search landscape effectively. Thus, we creatively propose the memristive evolutionary game: the diverse metal layers engage in a strategic interplay that determines the ownership hierarchy of chip macro modules and the 2D layout of these chip macro modules within each designated metal layer is orchestrated using evolutionary algorithm, which harness the power of game theoretic evolution to seek the optimal solution, balancing the objectives of minimizing layout area and wiring length. Upon comparison with alternative algorithms, the game evolution algorithm introduced in this paper exhibits superior optimization performance.

关键词： Wiring Navigation Layout Stacking Metals Games Evolutionary computation Computer architecture Complexity theory Optimization

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scroll Memristive Chaotic System via Fractal Process

A Multi-Scroll Memristive Chaotic System via Fractal Process

引用

International Conference on Information Science and Technology (ICIST)

作者： Liquan Xiao Shukai Duan Lidan Wang College of electronic and information engineering Southwest University Chongqing China National & Local Joint Engineering Southwest University Chongqing China Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Southwest University Chongqing China

Fractal theory is a leading and important branch of nonlinear science, which has been widely studied in many fields in the past few decades. Memristor is a nanoscale element with low power consumption and high integration, when it works as the nonlinear part in a chaotic system, the complexity of the chaotic system will be enhanced. Compared with single-scroll chaotic attractor, multi-scroll chaotic attractor have higher complexity and better adaptability. In this paper, the fractal process is applied to a known memristive chaotic system, which can generate multi-scroll chaotic attractor. At first, a fractal iteration is applied to the memristive chaotic system to generate new chaotic attractor. Secondly, the multi-scroll chaotic system is obtained by combining the Julia fractal and memristive chaotic system. And by changing a complex constant in the fractal process, a fractal graph with different shapes is obtained, which can also be used to generate different chaotic attractors in the generating multi-scroll memristive chaotic system. Compared with other multi-scroll chaotic attractors, the proposed multi-scroll chaotic attractors are easier to adjust the number of the scrolls. It can be seen from the simulation diagram that the size of the system phase diagram becomes smaller and smaller as the number of scrolls increases. The results show that the new system has a lot of dynamic characteristics.

关键词： Fractals Chaotic communication Memristors Complexity theory Electronic mail

来源：评论

学校读者我要写书评

暂无评论

NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks

arXiv

引用

arXiv 2024年

作者： Ma, Yuqi Wang, Huamin Shen, Hangchi Chen, Xuemei Duan, Shukai Wen, Shiping Southwest University Chongqing400715 China Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips Chongqing400715 China University of Technology Sydney Australian Institute of Artificial Ieintelligence Sydney2007 Australia

Recently, brain-inspired spiking neural networks (SNNs) have attracted great research attention owing to their inherent bio-interpretability, event-triggered properties and powerful perception of spatiotemporal information, which is beneficial to handling event-based neuromorphic datasets. In contrast to conventional static image datasets, event-based neuromorphic datasets present heightened complexity in feature extraction due to their distinctive time series and sparsity characteristics, which influences their classification accuracy. To overcome this challenge, a novel approach termed Neuromorphic Momentum Contrast Learning (NeuroMoCo) for SNNs is introduced in this paper by extending the benefits of self-supervised pre-training to SNNs to effectively stimulate their potential. This is the first time that self-supervised learning (SSL) based on momentum contrastive learning is realized in SNNs. In addition, we devise a novel loss function named MixInfoNCE tailored to their temporal characteristics to further increase the classification accuracy of neuromorphic datasets, which is verified through rigorous ablation experiments. Finally, experiments on DVS-CIFAR10, DVS128Gesture and N-Caltech101 have shown that NeuroMoCo of this paper establishes new state-of-the-art (SOTA) benchmarks: 83.6% (Spikformer-2-256), 98.62% (Spikformer-2-256), and 84.4% (SEW-ResNet-18), respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

High-Performance Sensing: Application of FPGA-based Winograd CNN Accelerator in Electronic Nose Systems

High-Performance Sensing: Application of FPGA-based Winograd...

引用

Artificial Intelligence and Computer Engineering (ICAICE), International Conference on

作者： Aolong Tan Shukai Duan Mingzhe Chen Ke Ding Changqing Li Lidan Wang State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China College of Artificial Intelligence Southwest University Chongqing China National & Local Joint Engineering Research Center of Intelligent Transmission and Control Technology China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips Chongqing China Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University) Ministry of Education Southwest University Chongqing PR China

ISBN: (数字)9798331528911

ISBN: (纸本)9798331528928

Electronic nose technology has been widely used in various scenarios such as industrial, military, food and environmental, and its recognition accelerator is responsible for completing the detection and identification of gases. Therefore, the application of advanced artificial intelligence algorithms to recognition accelerators is a common practice among researchers nowadays. However, neural networks with high recognition rates tend to have complex structures and a large number of parameters, which exacerbates the difficulty of deployment. To address this challenge, this paper first analyses and processes the detected gas data and proposes a hardware-friendly lightweight gas classification network, and then, based on this network, designs an FPGA-based Winograd CNN accelerator through the study of hardware implementation of Convolutional Neural Networks (CNN). The Winograd algorithm is used to reduce the number of multiplications used in the convolutional operation so as to reduce the consumption of hardware computing resources by the accelerator. Finally, the designed gas classification network is deployed on FPGA to complete the implementation of the recognition acceleration engine in the electronic nose system. The detection and recognition experiments on the laboratory gas dataset demonstrated good performance in terms of 99.5% recognition rate and only 2.94W power consumption of the accelerator, respectively.

关键词： Training Power demand Electronic noses Throughput Hardware Sensors Convolutional neural networks Object recognition Field programmable gate arrays Testing

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

Computer Science, Electronic Information Engineering and intelligent control Technology (CEI), IEEE International Conference on

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

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

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.

关键词： YOLO Performance evaluation Power demand Accuracy Convolution Computational modeling Memristors Hardware IP networks Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Model Based on Structure Attention Mechanism

Advances in Intelligent Systems and Computing

引用

Advances in intelligent Systems and computing 2018年 650卷 17-27页

作者： Lin, Kai Lin, Dazhen Cao, Donglin Cognitive Science Department Xiamen University Xiamen China Fujian Key Laboratory of Brain-Inspired Computing Technique and Applications Xiamen University Xiamen China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (纸本)9783319669380

Since the long short-term memory (LSTM) network is a sequential structure, it is difficult to effectively represent the structural level information of the context. Sentiment analysis based on the original LSTM causes a problem of structural level information loss, and its capacity to capture the context information is finite. To address this problem, we proposed a novel structure-attention-based LSTM as a hierarchical structure model. It may capture relevant information in the context as much as possible. We propose HM (ht matrix) to storage the structural information of the context. Furthermore, we introduce the attention mechanism to realize vector selection. Compared with the original LSTM and normal attention-based sentiment classification methods, our model obtains a higher classification precision. It is proved that the structure-attention-based method proposed in this study has an advantage in capturing the potential semantic structure. © 2018, Springer International Publishing AG.

关键词： Long short-term memory

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：