检索结果-内蒙古大学图书馆

Memristor-Based Circuit of Sequential Associative Memory with Memory Interactions and Stimulus Similarity Effect

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Xiong, Dongdong Wang, Xiaoping Jiang, Yiming Yang, Chao Jiang, Man Lai, Jingang Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Hubei Key Laboratory of Braininspired Intelligent Systems Wuhan430074 China Huazhong University of Science and Technology Institute of Artificial Intelligence School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Guangxi University of Science and Technology School of Computer Science and Technology Liuzhou545006 China Huazhong University of Science and Technology Department of Physiology School of Basic Medicine and Tongji Medical College Wuhan430030 China

Most proposed memristor-based circuits of associative memory consider various mechanisms in only one associative memory. Few works on circuit design of sequential associative memory have been reported. In this paper, a memristor-based circuit of sequential associative memory with memory interactions and stimulus similarity effect is designed. Two associative memories, the prior associative memory (PAM) and the later associative memory (LAM), are formed successively. The PAM modifies the rate of the formation of the LAM, and the LAM, in turn, affects the strength of the PAM, which are two interactions in sequential associative memory, called transfer and retroaction. In addition, the magnitudes of transfer and retroaction are determined by the similarity of the conditioned stimuli. The above functions are realized by the ring input processing module, memory module, transfer module and retroaction module. It has been identified in circuit analysis that the proposed circuit is power efficient and has good robustness. Furthermore, the proposed circuit has promising applications for fire rescue robots. © 2016 IEEE.

关键词： Associative storage

来源：评论

学校读者我要写书评

暂无评论

Relative-Posture-Fixed Model Predictive Human-Following Control with Visibility Constraints in Obstacle Environments 8

Relative-Posture-Fixed Model Predictive Human-Following Cont...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Zhang, Yikun Huang, Jian Yu, Jinqi Zhu, Yaonan Hasegawa, Yasuhisa School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory for Image Processing and Intelligent Control Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute ShenZhen518060 China Nagoya University Department of Micronano Mechanical Science and Engineering Nagoya464-8603 Japan

ISBN: (纸本)9798350300178

The relative-posture-fixed human following is critical for the human-robot interaction and cooperation in daily scenes such as domestic service and healthcare. However, few of previous researches have discussed the difficulties faced by mobile robots in the real world, including the limitation of sensing range and hindrance from obstacles. For practicality, in this paper we investigate the relative-posture-fixed following control with collision avoidance and visibility constraints. The control task is formulated as a receding-horizon optimization problem and solved under the Nonlinear Model Predictive Control (NMPC) framework, while an Extended Kalman Filter (EKF) based human trajectory predict algorithm is integrated into the robot controller. The effectiveness of the proposed algorithm is verified in a simulation, and the results demonstrate a promising performance of our controller for the human-following task in complicated environments. © 2023 IEEE.

关键词： Human robot interaction

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

arXiv

引用

arXiv 2023年

作者： Liu, Tianqi Ye, Xinyi Zhao, Weiyue Pan, Zhiyu Shi, Min Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 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 non-local 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-to-line 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. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Topic Embedded Representation Enhanced Variational Wasserstein Autoencoder for Text Modeling 5

Topic Embedded Representation Enhanced Variational Wasserste...

引用

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Xiang, Zheng Liu, Xiaoming Yang, Guan Liu, Yang Zhongyuan University of Technology School of Computer Science Zhengzhou China Henan Key Laboratory on Public Opinion Intelligent Analysis Zhengzhou China Key Laboratory of text processing and image understanding Zhengzhou China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Shandong University Key Lab of Cryptologic Technology and Information Security Ministry of Education Xi'an China

ISBN: (纸本)9781665485081

Variational Autoencoder (VAE) is now popular in modeling and language generation tasks, which need to pay attention to the diversity of generation results. The existing models are insufficient in capturing the built-in relationships between topic representation and sequential words. At the same time, there is a massive contradiction between the commonly used simple Gaussian prior and the actual complex distribution of languages. To address the above problems, we introduce a hybrid Wasserstein Autoencoder (WAE) with Topic Embedded Representation (TER) for modeling. TER is obtained through an embedding-based topic model and can capture the dependencies and semantic similarities between topics and words. In this case, the learned latent variable has rich semantic knowledge with the help of TER and is easier to explain and control. Our experiments show that our method is competitive with other VAEs in modeling. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning via Mean Field Approach 15

Adaptive Federated Learning via Mean Field Approach

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Tu, Kaifei Zheng, Shensheng Wang, Xuehe Hu, Xiping School of Artificial Intelligence Sun Yat-sen University Zhuhai China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen China

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

In order to solve the problem of "data island"and preserve individual's privacy, federated learning, as a distributed machine learning technology, has emerged recently. In federated learning, the model training is distributed over edge clients and coordinated by a central server. Each client only needs to send the updated model parameter to the central server for aggregation without sharing its private data. However, due to the data divergence of heterogeneous clients, the convergence rate of the global model training may be very slow, especially for non-IID data case. To deal with this issue and achieve fast convergence, we propose an adaptive learning rate strategy for each client by considering the deviation of the local model parameter from the global model parameter at each global training iteration. To enable decentralized learning rate design for each client, a mean-field scheme is introduced to estimate the global model parameters over time, which does not even require many clients to communicate frequently. Finally, we run numerical experiments to validate our results. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Cascading Failures in Interdependent Directed Networks Under Localized Attacks

SSRN

引用

SSRN 2023年

作者： Lv, Mengyu Pan, Linqiang Liu, Xueming Key Laboratory of Image Information Processing and Intelligent Control Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Many real-world systems interact with one another through dependency links, which reduces the system robustness. Most previous studies on the robustness of interdependent networks focus on undirected networks, and the related studies on directed networks are limited to random or targeted attacks. However, some failure scenarios can not be described by these two kinds of attacks, such as earthquakes, floods, and epidemics, where systems are attacked in a local range. In this work, we develop a theoretical framework for analyzing the robustness of interdependent directed networks under localized attacks. We find that for degree homogeneous networks, network robustness under localized attacks is similar to that under random attacks. There are four phase transitions in the phase diagram of the network, and a four-phase transition point and a two-phase transition point are found. For degree heterogeneous networks, localized attacks are more likely to lead to collapse than random attacks. As the coupling strength between networks increases, the interdependent networks first show a second order phase transition, and then a hybrid phase transition, and a first order phase transition at last. Furthermore, as the degree heterogeneity decreases, the robustness of networks first increases and then decreases, showing a local robustness maximum. The findings could help understand network robustness and enable better design of robust interdependent systems. © 2023, The Authors. All rights reserved.

关键词： Phase diagrams

来源：评论

学校读者我要写书评

暂无评论

Dynamic Residual Classifier for Class Incremental Learning

Dynamic Residual Classifier for Class Incremental Learning

引用

International Conference on Computer Vision (ICCV)

作者： Xiuwei Chen Xiaobin Chang School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal Invariant Hierarchical Molecular Representation for Out-of-distribution Molecular Property Prediction

Causal Invariant Hierarchical Molecular Representation for O...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wen, Xinlong Guo, Yifei Wei, Shuoying Long, Wenhan Zhu, Lida Zhu, Rongbo College of Informatics Huazhong Agricultural University Wuhan430070 China Shenzhen Institute of Nutrition and Health Huazhong Agricultural University Shenzhen518000 China Shenzhen Branch Guangdong Laboratory for Lingnan Modern Agriculture Genome Analysis Laboratory of the Ministry of Agriculture Agricultural Genomics Institute at Shenzhen Chinese Academy of Agricultural Sciences Shenzhen518000 China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Hubei Wuhan430074 China Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

ISBN: (纸本)9798350386226

Molecular representation learning is widely used in the field of drug discovery, due to its ability to accurately capture the complex features of compounds in high-dimensional space. However, existing molecular representation learning models are prone to be influenced by spurious parts during distribution shifts (also known as out-of-distribution, or OOD), which results in models mistakenly treating these spurious parts as crucial features of molecules, thereby limiting the generalization capability of the models. To tackle this issue, a novel invariant molecular representation learning model, called Causal Invariant Hierarchical Molecular Representation Graph Neural Networks (CHiMoGNN), is proposed for OOD molecular property prediction. In CHiMoGNN, a Feature Enhancement (FE) module is designed to leverage the multi-level molecular parts to enhance the expression of invariant features, thereby enhancing the model's capability to capture key molecular information. In addition, a Cartesian Product based Environmental Impact (EI) module is adopted to generate counterfactual samples with environmental diversity. Consequently, these samples are utilized to train a classifier that maintains consistent performance across various environments. Extensive experiments on seven real-world datasets demonstrate that CHiMoGNN outperforms 9 state-of-the-art models, achieving a 5.73% increase in average ROC-AUC, and the results also show that CHiMoGNN can effectively maintain generalization in various distribution shifts. Code and datasets are available at https://***/Chertuion/CHiMoGNN. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

arXiv

引用

arXiv 2024年

作者： Zhang, Huaxin Xu, Xiaohao Wang, Xiang Zuo, Jialong Huang, Xiaonan Gao, Changxin Zhang, Shanjun Yu, Li Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China University of Michigan Ann Arbor United States Kanagawa University Japan

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments. For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy. Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos. Our benchmark and model are publicly available at https: //***/pipixin321/HolmesVAU. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Proactive Resilient Day-Ahead Unit Commitment with Cloud Computing Data Centers

Proactive Resilient Day-Ahead Unit Commitment with Cloud Com...

引用

作者： Liu, Shengwei Zhao, Tianyang Liu, Xuan Li, Yuanzheng Wang, Peng Energy and Electricity Research Center Jinan University Zhuhai China School of Artificial Intelligence and Automation Ministry of Education Key Laboratory of Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

To enhance the resilience of power systems toward the temporal and spatial impacts caused by extreme weather events, e.g., hurricanes, the flexibility of cloud data centers (CDCs) is treated as a kind of efficient demand response. Since the workloads of CDCs have the shifting capacity between different locations and time slots, a day-ahead unit commitment problem including data centers is proposed to explore the integrated spatial and temporal flexibility of the workloads to its full extent through task migration. Considering the uncertainty of probability density functions, the line failure rates, workload arrival rates, power loads are integrated into an ambiguity set. The scheduling process of generators and CDCs is modeled as a two-stage distributionally robust optimization problem, which is reformulated as a large-scale deterministic mixed-integer linear programming problem and solved by the multicuts Benders decomposition method. The performance of the proposed scheduling strategy is tested in both the IEEE 24-bus RTS system and the three-area RTS-96 system. The results reveal that the method could mitigate the adverse impacts of hurricanes by enhancing the resilience of power systems and decreasing the dropping workloads of CDCs. © 1972-2012 IEEE.

关键词： Hurricanes

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：