检索结果-内蒙古大学图书馆

An Associative-Memory-Based Reconfigurable Memristive Neuromorphic System With Synchronous Weight Training

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2020年第3期12卷 529-540页

作者： Yang, Le Zeng, Zhigang Huang, Yi 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

Memristive neuromorphic systems are emerging potential hardware platforms to implement artificial neural networks. Combining features of memristive neuromorphic systems with associative memory, this article proposes an associative-memory-based reconfigurable memristive neuromorphic system. In the proposed system, there are two neural networks: 1) the neural network for computing acceleration and 2) the neural network mimicking associative memory. Then, a case study of the system is presented, which includes an associative memory network to realize apple recognition and a computing acceleration network for iris classification. The associative memory network depends on associative learning to achieve the recognition function. In addition, during the corresponding forgetting process, the connections of the related synaptic circuits are cut off and sent to a synaptic circuit block, realizing variable circuit topology. Further, the synaptic circuits in the block are applied to construct the iris classification network, accomplishing the reconfiguration of the proposed system. The circuit structure of this classification network matches backpropagation (BP) algorithm well. Meanwhile, the network reaches a relatively high classification accuracy after training. In an iteration of the training, all the synaptic circuits that need to change can adjust weights synchronously, which improves training speed.

关键词： Neuromorphics Neurons Associative memory Memristors Logic gates Threshold voltage Training Associative memory backpropagation (BP) algorithm memristive neuromorphic system memristor reconfigurable neuromorphic system synchronous weight training

来源：评论

学校读者我要写书评

暂无评论

Computationally Expensive High-Dimensional Multiobjective Optimization via Surrogate-Assisted Reformulation and Decomposition

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Pan, Linqiang Lin, Jianqing Wang, Handing He, Cheng Tan, Kay Chen Jin, Yaochu School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence Xidian University Xi’an China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong School of Engineering Trustworth and General Artificial Intelligence Laboratory Westlake University Hangzhou China

In recent decades, various surrogate-assisted evolutionary algorithms (SAEAs) have been proposed to solve computationally expensive multiobjective optimization problems (EMOPs). Nevertheless, designing an SAEA to handle high-dimensional EMOPs and balance convergence, diversity, and computational complexity remains challenging. Here, we propose a two-phase SAEA (TP-SAEA), which follows the idea of convergence first and diversity second, for solving high-dimensional EMOPs. In Phase I, a surrogate-assisted problem reformulation method is proposed to fast-track the Pareto optimal set in association with some reference solutions. Specifically, the high-dimensional EMOP is reformulated into an expensive single-objective one with low-dimensional decision space. Then, the surrogate-assisted optimization is utilized to obtain well-converged solutions. In Phase II, the high-dimensional EMOP is decomposed into two subproblems to explore subregions of the decision space that can effectively promote the diversity of the solutions. The two subproblems are optimized independently via surrogate-assisted optimization, aiming to push the population towards different regions of the Pareto optimal front. Experiments are conducted on EMOPs with 100 to 500 decision variables compared with four state-of-the-art SAEAs. The proposed TP-SAEA obtains well-converged and diverse solutions with only 509 real function evaluations. Moreover, its superiority is examined in six real-world instances with up to 12,000 decision variables. IEEE

关键词： Iron

来源：评论

学校读者我要写书评

暂无评论

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

arXiv

引用

arXiv 2021年

作者： Wu, Yuhang Huang, Tengteng Yao, Haotian Zhang, Chi Shao, Yuanjie Han, Chuchu Gao, Changxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Megvii Technology China

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intra-domain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Closer to pre-trained network transfer better 9

Closer to pre-trained network transfer better

引用

9th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2020

作者： Chen, Siyu Li, Wei Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Image Processing and Intelligent Control Key Laboratory Education Ministry of China Wuhan430074 China

In recent years, Deep Neural Network (DNN) has been widely used in the domain of computer vision, but its further development is restricted because of the lack of train samples. Fine-tuning is one of deep transfer learning methods to solve this problem. Nowdays, some existing Fine-tuning approaches assume that if the fine-tuned network could be as close to the pre-trained network as possible, the source knowledge would be fully utilized to improve the study effect. Although these approaches work pretty well, the assumptions on which they are based have not been systematically proved. Due to the complexity of DNNs, offering a reasonable and accurate explanation of the performance of the network is significant for designing new algorithms. In this paper, we design a series of experiments with or without transfer learning respectively, to characterize the relationship between network differences and network performance. The results show that there is an obvious negative correlation between them under certain circumstances. This conclusion can not only provide a more reasonable explanation for the relevant transfer learning algorithm, but also provide support and in-spiration for the future work. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Person Search with Region Siamese Networks

Weakly Supervised Person Search with Region Siamese Networks

引用

International Conference on Computer Vision (ICCV)

作者： Chuchu Han Kai Su Dongdong Yu Zehuan Yuan Changxin Gao Nong Sang Yi Yang Changhu Wang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ByteDance University of Technology Sydney

ISBN: (纸本)9781665428132

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM [36] and MGTS [4], by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field.

关键词： Training Computer vision Annotations Supervised learning Training data Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2020年第10期28卷 2570-2580页

作者： Wu, Dongrui Lin, Chin-Teng Huang, Jian Zeng, Zhigang Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Univ Technol Fac Engn & Informat Technol Sydney NSW 2006 Australia

Fuzzy systems have achieved great success in numerous applications. However, there are still many challenges in designing an optimal fuzzy system, e.g., how to efficiently optimize its parameters, how to balance the trade-off between cooperations and competitions among the rules, how to overcome the curse of dimensionality, how to increase its generalization ability, etc. Literature has shown that by making appropriate connections between fuzzy systems and other machine learning approaches, good practices from other domains may be used to improve the fuzzy systems, and vice versa. This article gives an overview on the functional equivalence between Takagi-Sugeno-Kang fuzzy systems and four classic machine learning approaches-neural networks, mixture of experts, classification and regression trees, and stacking ensemble regression-for regression problems. We also point out some promising new research directions, inspired by the functional equivalence, that could lead to solutions to the aforementioned problems. To our knowledge, this is so far the most comprehensive overview on the connections between fuzzy systems and other popular machine learning approaches, and hopefully will stimulate more hybridization between different machine learning algorithms.

关键词： Fuzzy systems Neural networks Machine learning Stacking Machine learning algorithms Fuzzy sets Regression tree analysis CART ensemble regression fuzzy systems mixture of experts neural networks stacking

来源：评论

学校读者我要写书评

暂无评论

Multi-scroll hidden attractor in memristive HR neuron model under electromagnetic radiation and its applications

引用

CHAOS 2021年第1期31卷 011101页

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

This paper aims to propose a novel no-equilibrium Hindmarsh-Rose (HR) neuron model with memristive electromagnetic radiation effect. Compared with other memristor-based HR neuron models, the uniqueness of this memristive HR neuron model is that it can generate multi-scroll hidden attractors with sophisticated topological structures and the parity of the scrolls can be controlled conveniently with changing the internal parameters of the memristor. In particular, the number of scrolls of the multi-scroll hidden attractors is also associated with the intensity of external electromagnetic radiation stimuli. The complex dynamics is numerically studied through phase portraits, bifurcation diagrams, Lyapunov exponents, and a two-parameter diagram. Furthermore, hardware circuit experiments are carried out to demonstrate theoretical analyses and numerical simulations. From the perspective of engineering application, a pseudo-random number generator is designed. Besides, an image encryption application and security analysis are also performed. The obtained results show that the memristive HR neuron model possesses excellent randomness and high security, which is suitable for chaos-based real-world applications. Published under license by AIP Publishing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine discovery of partial differential equations from spatiotemporal data: A sparse Bayesian learning framework

引用

CHAOS 2023年第11期33卷 113122页

作者： Yuan, Ye Li, Xiuting Li, Liang Jiang, Frank J. Tang, Xiuchuan Zhang, Fumin Goncalves, Jorge Voss, Henning U. Ding, Han Kurths, Juergen Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat State Key Lab Digital Mfg Equipments & Technol Wuhan 430074 Peoples R China Huazhong Agr Univ Coll Informat Wuhan 430070 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China KTH Royal Inst Technol Div Decis & Control Syst S-10044 Stockholm Sweden Tsinghua Univ Sch Automat Beijing 100084 Peoples R China Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30309 USA Univ Cambridge Dept Engn Cambridge England Univ Luxembourg Luxembourg Ctr Syst Biomed L-4362 Belvaux Esch Sur Alzett Luxembourg Cornell Univ Coll Human Ecol Cornell MRI Facil Ithaca NY 10065 USA Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Digital Mfg Equipments & Technol Wuhan 430074 Peoples R China Potsdam Inst Climate Impact Res Res Domain IV Transdisciplinary Concepts & Methods D-14412 Potsdam Germany

This study presents a general framework, namely, Sparse Spatiotemporal System Discovery (S(3)d), for discovering dynamical models given by Partial Differential Equations (PDEs) from spatiotemporal data. S(3)d is built on the recent development of sparse Bayesian learning, which enforces sparsity in the estimated PDEs. This approach enables a balance between model complexity and fitting error with theoretical guarantees. The proposed framework integrates Bayesian inference and a sparse priori distribution with the sparse regression method. It also introduces a principled iterative re-weighted algorithm to select dominant features in PDEs and solve for the sparse coefficients. We have demonstrated the discovery of the complex Ginzburg-Landau equation from a traveling-wave convection experiment, as well as several other PDEs, including the important cases of Navier-Stokes and sine-Gordon equations, from simulated data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Locating and Sizing Charging Station in Multi-Period to Promote Electric Vehicles Adoption in Urban Areas

SSRN

引用

SSRN 2023年

作者： Hu, Dandan Huang, Liu Liu, Chen Liu, Zhi-Wei The School of Management South-central Minzu University Wuhan430074 China The School of Engineering RMIT University MelbourneVIC3001 Australia The School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

The layout of public fast charging stations often fails to meet the charging demand of electric vehicle (EV) users, resulting in charging anxiety. To address this issue and promote the widespread use of EVs in urban areas, this paper presents a multiperiod locating and sizing optimization model under dynamic demand. The model incorporates GPS trajectory extraction data to identify potential charging demand points and considers the mobile load characteristics of EVs for fusion modeling. A multiperiod change formula is proposed to reflect the interaction between public fast charging stations and EV market penetration, incorporating charging opportunity and waiting time satisfaction as measures of charging service quality. To solve the model, a heuristic algorithm combining genetic algorithm (GA) and k-medoids clustering algorithm is designed. We apply the model to an actual case of Shenzhen and find that increasing investment in charging infrastructure can boost EV market penetration in the later planning period. Moreover, the gap between charging opportunity and waiting time satisfaction tends to narrow as the planning progresses. Our findings highlight the importance of optimizing the location and size of public fast charging stations to improve the charging service quality and promote the adoption of EVs. © 2023, The Authors. All rights reserved.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A Risk-Based Dynamic Decision-Making Approach for Cybersecurity Protection in Industrial control Systems

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2020年第10期50卷 3863-3870页

作者： Qin, Yuanqing Zhang, Qi Zhou, Chunjie Xiong, Naixue Huazhong Univ Sci & Technol Sch Automat Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China Southwestern Oklahoma State Univ Dept Business & Comp Sci Weatherford OK 74078 USA

Decision-making is a key component of industrial control system (ICS) security. However, due to the stability and real-time requirements of ICSs, current decision-making approaches typically designed for IT systems are not entirely suitable for ICSs. In this paper, with consideration of the characteristics of ICSs, a risk-based multistep dynamic decision-making approach for protecting ICSs is proposed. Following this proposal, multiple models, including multilayer Bayesian network, process model, and attack-defense strategy model are built first. On this basis, a state controller is designed to ensure the safe degradation/upgradation of ICSs. Finally, a game theory-based optimal defense strategy generation approach is presented. To verify the effectiveness of the proposed approach, a simulation on a simplified chemical reactor control system is conducted in MATlab. The simulation results clearly demonstrate that the proposed dynamic decision-making approach has the ability to generate the optimal defense strategy to minimize system loss.

关键词： Decision making Degradation Computer security Production Integrated circuits Bayes methods Cybersecurity dynamic decision-making industrial control systems (ICS) intrusion response

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：