检索结果-内蒙古大学图书馆

Full-Circuit Implementation of Transformer Network Based on Memristor

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2022年第4期69卷 1395-1407页

作者： Yang, Chao Wang, Xiaoping Zeng, Zhigang Huazhong Univ Sci & Technol Inst Artificial Intelligence Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China Guangxi Univ Sci & Technol Sch Elect Elect & Comp Sci Liuzhou 545006 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

As an emerging in-memory element, memristor has been widely used in various neural network circuits to represent the weights and accelerate the calculation. However, the Transformer Network (TN), one of the most important models for machine vision and natural language processing in recent years, has not yet been full-circuit implemented using memristors due to the complex calculation process and data storage. In order to carry out the computation of the TN more efficiently, this work proposes a memristor-based full-circuit implementation of the TN capable of: 1) a memristor crossbar module to preserve the weights of the TN and perform the vector-matrix multiplications;2) an analog signal memory module to store the analog signal directly in near-memory mode;3) function circuit modules to achieve five transformations, namely Softmax, Layer Normalization, ReLU, Multiply-add and Residual;4) a timing signal generation module to schedule operations of the circuit. The proposed TN circuit can complete all calculations directly based on the analog signal without using any analog-digital converter (ADC), digital-analog converter (DAC) and digital memory. In addition, character image recognition experiments are carried out in PSPICE to verify the functional correctness of the designed circuit. The corresponding signal retention rates of the analog memory, the performance of the whole circuit, and the non-idealities of the memristors are also analyzed. The results indicate that the circuit has advantages in terms of area overhead, energy efficiency and anti-noise.

关键词： Memristors Transformers Neural networks Data models Task analysis image recognition Computational modeling Memristor transformer network analog signal memory circuit implementation

来源：评论

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

Isoform Function Prediction Based on Heterogeneous Graph Att...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Guo, Kuo Li, Yifan Chen, Hao Shen, Hong-Bin Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Image Processing and Pattern Recognition Shanghai200240 China Carnegie Mellon University School of Computer Science Computational Biology Department PittsburghPA15213 United States

ISBN: (纸本)9798350337488

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function. © 2023 IEEE.

关键词： alternative splicing gene ontology heterogeneous graph attention network isoform function prediction protein language model

来源：评论

学校读者我要写书评

暂无评论

image saliency detection method based on multi-feature maps fusion 4

Image saliency detection method based on multi-feature maps ...

引用

4th International Conference on Computer Graphics, image, and Virtualization, ICCGIV 2024

作者： Li, Xiaoli Liu, Yunpeng Zhao, Huaici Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Shenyang China The Key Lab of Image Understanding and Computer Vision Shenyang China Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510683242

In this research, we introduce an innovative saliency detection algorithm, comprising three essential steps. Firstly, leveraging fully convolutional networks with aggregation interaction modules, we generate an initial saliency map. Secondly, we extract hand-craft and deep features to express the image, then use manifold ranking method to construct saliency maps. Ultimately, by integrating the outcomes from preceding stages, we generate the final saliency map. Experimental findings demonstrate that our method surpasses twelve cutting-edge saliency detection techniques in terms of precision, recall, F-measure, and MAE value metrics." © 2024 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Boundary effects on road network vulnerability in cities

引用

CITIES 2024年 154卷

作者： Cheng, Zekai Ouyang, Min Du, Chongyang Hong, Liu Wang, Hongwei Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Management Wuhan 430074 Peoples R China

Road networks are typically connected at the national scale, thus investigating a city's road network vulnerability requires defining an urban boundary. However, the choice of boundary varies widely in research, resulting in divergent and at times contradictory findings. Moreover, analyzing larger cities' road networks with expanding boundaries helps to predict road network vulnerability patterns in smaller, similarly structured cities. Guided by these two objectives, this study investigates the gaps in road network vulnerabilities by comparing 1452 road networks from 363 cities in Mainland China across four distinct boundary types. The findings indicate a significant change in road network vulnerability across different boundaries, with the largest gap ranging between 0.5449 and 0.8743. The study further finds these vulnerability gaps correlate with the difference in the structural characteristics of those urban road networks and the urban population covered by different boundaries, with correlation coefficients ranging from 0.362 to 0.755. Notably, the cities' vulnerability rankings show relatively slight variations when adopting different boundaries, with Spearman's correlation coefficients between 0.442 and 0.879. This research offers valuable insights into the influence of urban expansion on road network vulnerability, particularly relevant in the context of rapid urbanization and the expansion of road networks.

关键词： Boundary Effects Urban Road Network Vulnerability

来源：评论

学校读者我要写书评

暂无评论

Formation tracking of multiple rectangular agents based on fully distributed observer

引用

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 2024年第9期361卷

作者： Chi, Jun Su, Housheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Mini Luoyu Rd 1037 Wuhan 430074 Hubei Peoples R China

In most existing studies, formation tracking algorithms are generally based on state feedback strategies and assume that agents are treated as points. However, in practical scenarios, directly obtaining the state of the target can often be challenging, and agents may have their own shapes. In this paper, we model agents as rectangles, allowing each agent to establish a safety zone to avoid collisions during formation. Based on these rectangular agents, we design formation tracking algorithms for a mobile target using only local output information. Specifically, two layers of control algorithms are designed for each agent. (1) Upper -level algorithm: two types of fully distributed mobile observers are constructed based on only a portion of the target's output information. This is achieved by applying node -based adaptive coupling gains and edgebased adaptive gains to the consensus -based term in the state estimation algorithm, respectively. (2) Lower -level algorithm: a leader -following formation tracking algorithm is constructed. By cascading these two layers of algorithms, all agents track the target in formation at the same speed as the target. Finally, numerical simulations are presented to demonstrate the effectiveness of the proposed theoretical results.

关键词： Distributed observer Formation tracking Rectangular agents

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Learning-Based 6-DOF Grasp Planning Method for Manipulator

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2022年第4期19卷 3639-3648页

作者： Peng, Gang Ren, Zhenyu Wang, Hao Li, Xinde Khyam, Mohammad Omar Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China Cent Queensland Univ Sch Engn & Technol Melbourne Vic 3000 Australia

To realize a robust robotic grasping system for unknown objects in an unstructured environment, large amounts of grasp data and 3D model data for the object are required;the sizes of these data directly affect the rate of successful grasps. To reduce the time cost of data acquisition and labeling and increase the rate of successful grasps, we developed a self-supervised learning mechanism to control grasp tasks performed by manipulators. First, a manipulator automatically collects the point cloud for the objects from multiple perspectives to increase the efficiency of data acquisition. The complete point cloud for the objects is obtained using the hand-eye vision of the manipulator and the truncated signed distance function algorithm. Then, the point cloud data for the objects are used to generate a series of six-degrees-of-freedom grasp poses, and the force-closure decision algorithm is used to add the grasp quality label to each grasp pose to realize the automatic labeling of grasp data. Finally, the point cloud in the gripper closing area corresponding to each grasp pose is obtained and used to train the grasp-quality classification model for the manipulator. The results of performing actual grasping experiments demonstrate that the proposed self-supervised learning method can increase the rate of successful grasps for the manipulator.

关键词： Manipulators Data models Point cloud compression Planning Grasping Three-dimensional displays Solid modeling Manipulator grasp planning self-supervised learning 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo

When Epipolar Constraint Meets Non-local Operators in Multi-...

引用

International Conference on Computer Vision (ICCV)

作者： Tianqi Liu Xinyi Ye Weiyue Zhao Zhiyu Pan Min Shi Zhiguo Cao Ministry of Education School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain nonlocal feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-toline search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is available at https://***/TQTQliu/ET-MVSNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Bayesian Koopman Learning Method for Modeling Hysteresis Dynamics

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第11期35卷 15615-15623页

作者： Huang, Xiang Zhang, Hai-Tao Wang, Jun Huazhong Univ Sci & Technol Engn Res Ctr Autonomous Intelligent Unmanned Syst Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China City Univ Hong Kong Sch Data Sci Hong Kong Peoples R China

Exploring the mechanism of hysteresis dynamics may facilitate the analysis and controller design to alleviate detrimental effects. Conventional models, such as the Bouc-Wen and Preisach models consist of complicated nonlinear structures, limiting the applications of hysteresis systems for high-speed and high-precision positioning, detection, execution, and other operations. In this article, a Bayesian Koopman (B-Koopman) learning algorithm is therefore developed to characterize hysteresis dynamics. Essentially, the proposed scheme establishes a simplified linear representation with time delay for hysteresis dynamics, where the properties of the original nonlinear system are preserved. Furthermore, model parameters are optimized via sparse Bayesian learning together with an iterative strategy, which simplifies the identification procedure and reduces modeling errors. Extensive experimental results on piezoelectric positioning are elaborated to substantiate the effectiveness and superiority of the proposed B-Koopman algorithm for learning hysteresis dynamics.

关键词： Hysteresis Heuristic algorithms Nonlinear dynamical systems Bayes methods Power system dynamics Learning systems Brain modeling Hysteresis Koopman operator modeling piezoelectric actuators (PEAs)

来源：评论

学校读者我要写书评

暂无评论

Global Stability of Bidirectional Associative Memory Neural Networks With Multiple Time-Varying Delays

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第6期52卷 4095-4104页

作者： Sheng, Yin Zeng, Zhigang Huang, Tingwen Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Texas A&M Univ Qatar Dept Sci Doha Qatar

This article investigates the global stability of bidirectional associative memory neural networks with discrete and distributed time-varying delays (DBAMNNs). By employing the comparison strategy and inequality techniques, global asymptotic stability (GAS) and global exponential stability (GES) of the underlying DBAMNNs are of concern in terms of p-norm (p >= 2). Meanwhile, GES of the addressed DBAMNNs is also analyzed in terms of 1-norm. When distributed time delay is neglected, the GES of the corresponding bidirectional associative memory neural networks is presented as an M-matrix, which includes certain existing outcomes as special cases. Two examples are finally provided to substantiate the validity of theories.

关键词： Bidirectional associative memory neural networks (BAMNNs) discrete-time delay distributed time delay global stability

来源：评论

学校读者我要写书评

暂无评论

Demand-Side Frequency control in Power Network Based on Multi-Agent Deep Reinforcement Learning

Demand-Side Frequency Control in Power Network Based on Mult...

引用

International Conference on Industrial Artificial Intelligence (IAI)

作者： Xianggang Liu Zhi-Wei Liu Ming Chi Yifan Zhang Key Laboratory of Image Processing and Intelligent Control Ministry of Education College of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

The integration of renewable energy sources into the power grid has led to new challenges in maintaining the stability of the system frequency. This paper proposes a novel approach to address the Optimal Demand Side Frequency control (ODFC) problem using Multi-Agent Deep Deterministic Policy Gradient (MADDPG) method. The proposed method models the ODFC problem as a Markov game, with centralized training based on multi-agent cooperative self-learning and associative storage service. In the decentralized execution stage, each agent independently outputs control actions to the controlled plant using local observations. Numerical simulations show that the proposed method effectively addresses the ODFC problem with superior performance compared to traditional methods.

关键词：

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：