检索结果-内蒙古大学图书馆

Spiking Neural P Systems with Polarizations and Rules on Synapses

COMPLEXITY 2020年第1期2020卷

作者： Jiang, Suxia Fan, Jihui Liu, Yijun Wang, Yanfeng Xu, Fei Zhengzhou Univ Light Ind Sch Elect & Informat Engn Henan Key Lab Informat Based Elect Appliances Zhengzhou 450002 Henan Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Educ Minist China Wuhan 430074 Hubei Peoples R China

Spiking neural P systems are a class of computation models inspired by the biological neural systems, where spikes and spiking rules are in neurons. In this work, we propose a variant of spiking neural P systems, called spiking neural P systems with polarizations and rules on synapses (PSNRS P systems), where spiking rules are placed on synapses and neurons are associated with polarizations used to control the application of such spiking rules. The computation power of PSNRS P systems is investigated. It is proven that PSNRS P systems are Turing universal, both as number generating and accepting devices. Furthermore, a universal PSNRS P system with 151 neurons for computing any Turing computable functions is given. Compared with the case of SN P systems with polarizations but without spiking rules in neurons, less number of neurons are used to construct a universal PSNRS P system.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Global Consensus for Heterogeneous Saturated Multi-Agent Systems via Sampled-Data control

Global Consensus for Heterogeneous Saturated Multi-Agent Sys...

引用

IEEE Conference on Decision and control

作者： Juan Qian Xiaoling Wang Daniele Astolfi Housheng Su Guo-Ping Jiang College of Automation and the College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Engineering Center for IOT Intelligent Robots(IOTRobot) Nanjing China CNRS LAGEPP UMR 5007 43 boulevard du 11 novembre 1918 Université Claude Bernard Lyon 1 Villeurbanne France Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai China School of Artificial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Luoyu Road 1037 Wuhan China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper addresses the global consensus problem for multi-input multi-output saturated systems within a sampled-data framework, aiming to advance global consensus, manage heterogeneous actuator saturation across components, and preserve distributed characteristics by using sampled-data feedback. We propose a distributed control algorithm that incorporates a redesigned saturation function, represented as decentralized dynamic saturation levels. These levels for each agent’s dimensions are autonomously updated through an adaptive strategy, which mitigates heterogeneous saturation by carefully selecting constant and time-varying saturation parameters in it. Lyapunov analysis proves that global consensus can be achieved under the proposed control law, provided the sampling periods of all agents remain below a calculated threshold. An example is given to demonstrate the effectiveness of this approach.

关键词： Actuators Upper bound Heuristic algorithms Decentralized control Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis with unlabeled or insufficient labeled data

引用

NEUROCOMPUTING 2020年 409卷 35-45页

作者： Cheng, Cheng Zhou, Beitong Ma, Guijun Wu, Dongrui Yuan, Ye Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat MOE Key Lab Intelligent Control & Image Proc Wuhan 430074 Peoples R China State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China

intelligent fault diagnosis is one critical topic of maintenance solution for mechanical systems. Deep learning models, such as convolutional neural networks (CNNs), have been successfully applied to fault diagnosis tasks and achieved promising results. However, one is that two datasets (in source and target domains) of similar tasks are with different feature distributions because of different operational conditions;another one is that insufficient or unlabeled data in real industry applications (target domains) limit the adaptability of the source domain well-defined models. To solve the above problems, the concept of transfer learning should be adopted for domain adaptation, in the meantime, a network performs both supervised and unsupervised learning is required. Inspired by Wasserstein distance of optimal transport, in this paper, we propose a novel Wasserstein Distance-based Deep Transfer Learning (WD-DTL) network for both supervised and unsupervised fault diagnosis tasks. WD-DTL learns domain feature representations (generated by a CNN based feature extractor) and minimizes distributions between the source and target domains through an adversarial training process. The effectiveness of the proposed WD-DTL is verified through 16 different transfer tasks. Results show that WD-DTL achieves the highest diagnostic accuracies when compared to the existing Maximum Mean Discrepancy and CNN networks in almost all transfer tasks. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Transfer learning Domain adaptation Wasserstein distance Convolutional neural networks intelligent fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Hilbert words as arrays generated with P systems

引用

JOURNAL OF MEMBRANE COMPUTING 2021年第3期3卷 163-169页

作者： Ceterchi, Rodica Zhang, Luping Subramanian, K. G. Zhang, Gexiang Univ Bucharest Fac Math & Comp Sci Acad St 14 Bucharest 010014 Romania Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist China Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Peoples R China Liverpool Hope Univ Fac Sci Hope Pk Liverpool L16 9JD Merseyside England Chengdu Univ Informat Technol Sch Control Engn Chengdu 610225 Peoples R China

Construction of finite grammars to generate languages of digitized picture patterns, considered as arrays of symbols, has been a problem of interest in two-dimensional formal languages. On the other hand, in the area of membrane computing, P systems were developed for handling the problem of picture array generation, with the rewriting involved being sequential or parallel. We introduce in this paper the array representation for the Hilbert words, the finite approximations of the Hilbert space-filling curve, and we generate them with array-rewriting rules in P systems. The array rewriting is done in parallel, with the P system serving as a control mechanism. A main contribution is the proof of correctness which is done using a linearization procedure. In addition, the advantage of the P system used is that the number of membranes involved is small (only one or two).

关键词： Membrane computing Parallel rewriting Array grammars Chain code words Hilbert's space-filling curve

来源：评论

学校读者我要写书评

暂无评论

image Fuzzy Edge Information Segmentation Based on Computer Vision and Machine Learning

引用

JOURNAL OF GRID COMPUTING 2023年第4期21卷 56-56页

作者： Luo, Tianye Li, Shijun Li, Ji Guo, Jie Feng, Ruilong Mu, Ye Hu, Tianli Sun, Yu Guo, Ying Gong, He Jilin Agr Univ Coll Informat Technol Changchun 130118 Jilin Peoples R China Wuzhou Univ Guangxi Key Lab Machine Vis & Intelligent Control Wuzhou 543002 Guangxi Peoples R China Wuzhou Univ Guangxi Coll & Univ Key Lab Image Proc & Intellige Wuzhou 543002 Guangxi Peoples R China Jilin Agr Univ Jilin Prov Agr Internet Things Technol Collaborat Changchun 130118 Jilin Peoples R China Jilin Agr Univ Jilin Prov Intelligent Environm Engn Res Ctr Changchun 130118 Jilin Peoples R China Jilin Agr Univ Jilin Prov Informat Technol & Intelligent Agr Engn Changchun 130118 Jilin Peoples R China

image segmentation is a key problem in the field of machine vision. Its core goal is to separate the target and background in the region of interest from the image and directly affect the accuracy of subsequent operations such as target recognition and image understanding. In the past decades, there have been many good image segmentation algorithms. In recent years, the deep learning method represented by deep learning has made great progress in the field of image segmentation. In this paper, some commonly used image segmentation algorithms based on machine learning were reviewed, and their theoretical and experimental studies were carried out. In this paper, the application prospect of machine learning in image segmentation was prospected. The existing image segmentation methods are mainly divided into the following categories: threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and segmentation methods based on specific theories. In recent years, with the rapid progress of computer vision technology, the requirements for the accuracy of object image edge information segmentation have become increasingly high. The main reason for image segmentation is to better obtain object information. However, due to interference conditions such as lighting and noise, image blurry edge information segmentation has become the most difficult point in the development of computer vision technology. In the comparative experiment of algorithms, the results showed that in the training set, the response time of Deep Neural Network (DNN) algorithm, Cluster Analysis (CA) algorithm, and Support Vector Machine (SVM) algorithm was 13.72 s, 16.88 s and 17.29 s when the number of samples was 150. In the test set, when the sample number was 50, the recognition rate of DNN algorithm was 93.7%;the recognition rate of CA algorithm was 87.9%;the recognition rate of SVM algorithm was 84.3%. Therefore, the research of image fuzzy edge information

关键词： Blurred Edges image Segmentation Machine Learning Computer Vision Deep Neural Network Cluster Analysis

来源：评论

学校读者我要写书评

暂无评论

An advanced actor-critic algorithm for training video game ai 1st

An advanced actor-critic algorithm for training video game a...

引用

1st International Conference on Neural Computing for Advanced Applications, NCAA 2020

作者： Zha, Zhong Yi Tang, Xue Song Wang, Bo Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Artificial Intelligence and Automation School Huazhong University of Science and Technology Wuhan430074 China College of Information and Science Donghua University Shanghai China

ISBN: (纸本)9789811576690

This paper presents an improved deep reinforcement learning (DRL) algorithm, namely Advanced Actor Critic (AAC), which is based on Actor Critic (AC) algorithm, to the video game Artificial intelligence (AI) training. The advantage distribution estimator, Normal Constraint (NC) function and exploration based on confidence are introduced to improve the AC algorithm, in order to achieve accurate value estimate, select continuous spatial action correctly, and explorate effectively. The aim is to improve the performance of conventional AC algorithm in a complex environment. A case study of video game StarCraft II mini-game AI training is employed. The results verify that the improved algorithm effectively improves the performance in terms of the convergence rate, maximum reward, average reward in every 100 episode, and time to reach a specific reward, etc. The analysis on how these modifications improve the performance is also given through interpretation of the feature layers in the mini-games. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A simple no-equilibrium chaotic system with only one signum function for generating multidirectional variable hidden attractors and its hardware implementation

引用

CHAOS 2020年第5期30卷 053129页

作者： Zhang, Sen Wang, Xiaoping Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

This paper proposes a simple no-equilibrium chaotic system with only one signum function as compared with the existing no-equilibrium chaotic ones with at least one quadratic or higher nonlinearity. The system has the offset boosting of three variables through adjusting the corresponding controlled constants. The resulting hidden attractors can be distributed in a 1D line, a 2D lattice, a 3D grid, and even in an arbitrary location of the phase space. Particularly, a hidden chaotic bursting oscillation is also observed in this system, which is an uncommon phenomenon. In addition, complex hidden dynamics is investigated via phase portraits, time series, Kaplan-Yorke dimensions, bifurcation diagrams, Lyapunov exponents, and two-parameter bifurcation diagrams. Then, a very simple hardware circuit without any multiplier is fabricated, and the experimental results are presented to demonstrate theoretical analyses and numerical simulations. Furthermore, the randomness test of the chaotic pseudo-random sequence generated by the system is tested by the National Institute of Standards and Technology test suite. The tested results show that the proposed system has good randomness, thus being suitable for chaos-based applications such as secure communication and image encryption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MADNet: A Fast and Lightweight Network for Single-image Super Resolution

引用

IEEE TRANSACTIONS ON CYBERNETICS 2021年第3期51卷 1443-1453页

作者： Lan, Rushi Sun, Long Liu, Zhenbing Lu, Huimin Pang, Cheng Luo, Xiaonan Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Kyushu Inst Technol Dept Mech & Control Engn Kitakyushu Fukuoka 8048550 Japan Guilin Univ Elect Technol Natl Local Joint Engn Res Ctr Satellite Nav & Loc Guilin 541004 Peoples R China

Recently, deep convolutional neural networks (CNNs) have been successfully applied to the single-image super-resolution (SISR) task with great improvement in terms of both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). However, most of the existing CNN-based SR models require high computing power, which considerably limits their real-world applications. In addition, most CNN-based methods rarely explore the intermediate features that are helpful for final image recovery. To address these issues, in this article, we propose a dense lightweight network, called MADNet, for stronger multiscale feature expression and feature correlation learning. Specifically, a residual multiscale module with an attention mechanism (RMAM) is developed to enhance the informative multiscale feature representation ability. Furthermore, we present a dual residual-path block (DRPB) that utilizes the hierarchical features from original low-resolution images. To take advantage of the multilevel features, dense connections are employed among blocks. The comparative results demonstrate the superior performance of our MADNet model while employing considerably fewer multiadds and parameters.

关键词： Feature extraction Computational modeling image reconstruction image resolution Task analysis Computer architecture Cybernetics Channel attention dense connections image super resolution lightweight multiscale mechanism

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Nonconvex Distributed Stochastic Zeroth-order Coordinate Method 60

Convergence Analysis of Nonconvex Distributed Stochastic Zer...

引用

60th IEEE Conference on Decision and control (CDC)

作者： Zhang, Shengjun Dong, Yunlong Xie, Dong Yao, Lisha Bailey, Colleen P. Fu, Shengli Univ North Texas Dept Elect Engn OSCAR Lab Denton TX 76207 USA Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat MOE 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 Univ North Texas Dept Elect Engn Denton TX 76207 USA

ISBN: (纸本)9781665436595

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of n local cost functions. We solve such a problem by involving zeroth-order (ZO) information exchange. In this paper, we propose a ZO distributed primal-dual coordinate method (ZODIAC) to solve the stochastic optimization problem. Agents approximate their own local stochastic ZO oracle along with coordinates under an adaptive smoothing parameter. We show that the proposed algorithm achieves the convergence rate of O(root p/root T) for general nonconvex cost functions. We demonstrate the efficiency of proposed algorithms through a numerical example in comparison with the existing state-of-the-art centralized and distributed ZO algorithms.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

arXiv

引用

arXiv 2022年

作者： Liu, Tianying Zhang, Lu Wang, Yang Guan, Jihong Fu, Yanwei Zhao, Jiajia Zhou, Shuigeng Department of Computer Science and Technology Tongji University Shanghai201804 China The Project Management Office of China National Scientific Seafloor Observatory Tongji University Shanghai200092 China Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200438 China Shanghai Key Lab of Intelligent Information Processing The School of Data Science Fudan University Shanghai200433 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [58, 59, 74, 78] that systematically study and compare them as the groups of fine-tuning/transfer learning, and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented. Copyright © 2022, The Authors. All rights reserved.

关键词： Object 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：