检索结果-内蒙古大学图书馆

Asian control Conference

作者： Guangzheng Ding Jian Huang Bin Hu Zhi-Hong Guan Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei P.R. China

ISBN: (纸本)9781509015740;9781509015733

The essential feature of conventional proxy-based sliding mode control (PSMC) method is the introduction of a proxy, which is controlled by a normal sliding mode control (SMC) approach to track the desired trajectory. Both the safety problem in conventional stiff position control and the chattering problem in the SMC are overcome by the PSMC strategy. Meanwhile, the stability problem of PSMC is not well addressed for general nonlinear systems. In this paper, a new PSMC method is proposed for robust tracking control of a class of second-order nonlinear systems. A PD type virtual coupling is used and a specified sliding mode controller is designed in the proposed PSMC method. Based on the model of a class of second-order nonlinear systems, the stability of the closed-loop PSMC system is proved by Lyapunov theorem. Numerical simulations were carried out to verify the propose method.

关键词： Nonlinear systems Force Couplings Stability analysis Robustness Sliding mode control Safety

来源：评论

学校读者我要写书评

暂无评论

Empirical studies on the properties of linear regions in deep neural networks

arXiv

引用

arXiv 2020年

作者： Zhang, Xiao Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

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

Optimize TSK fuzzy systems for regression problems: Mini-batch gradient descent with regularization, droprule, and adabound (MBGD-RDA)

arXiv

引用

arXiv 2019年

作者： Wu, Dongrui Yuan, Ye Huang, Jian Tan, Yihua Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Takagi-Sugeno-Kang (TSK) fuzzy systems are very useful machine learning models for regression problems. However, to our knowledge, there has not existed an efficient and effective training algorithm that ensures their generalization performance, and also enables them to deal with big data. Inspired by the connections between TSK fuzzy systems and neural networks, we extend three powerful neural network optimization techniques, i.e., mini-batch gradient descent (MBGD), regularization, and AdaBound, to TSK fuzzy systems, and also propose three novel techniques (DropRule, DropMF, and Drop-Membership) specifically for training TSK fuzzy systems. Our final algorithm, MBGD with regularization, DropRule and AdaBound (MBGD-RDA), can achieve fast convergence in training TSK fuzzy systems, and also superior generalization performance in testing. It can be used for training TSK fuzzy systems on datasets of any size;however, it is particularly useful for big datasets, on which currently no other efficient training algorithms exist. Copyright © 2019, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

TransView: Inside, Outside, and Across the Cropping View Boundaries

TransView: Inside, Outside, and Across the Cropping View Bou...

引用

International Conference on Computer Vision (ICCV)

作者： Zhiyu Pan Zhiguo Cao Kewei Wang Hao Lu Weicai Zhong Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Huawei CBG

ISBN: (纸本)9781665428132

We show that relation modeling between visual elements matters in cropping view recommendation. Cropping view recommendation addresses the problem of image recomposition conditioned on the composition quality and the ranking of views (cropped sub-regions). This task is challenging because the visual difference is subtle when a visual element is reserved or removed. Existing methods represent visual elements by extracting region-based convolutional features inside and outside the cropping view boundaries, without probing a fundamental question: why some visual elements are of interest or of discard? In this work, we observe that the relation between different visual elements significantly affects their relative positions to the desired cropping view, and such relation can be characterized by the attraction inside/outside the cropping view boundaries and the repulsion across the boundaries. By instantiating a transformer-based solution that represents visual elements as visual words and that models the dependencies between visual words, we report not only state-of-the-art performance on public benchmarks, but also interesting visualizations that depict the attraction and repulsion between visual elements, which may shed light on what makes for effective cropping view recommendation.

关键词： Visualization Computer vision Computational modeling Benchmark testing Feature extraction Transformers Decoding

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Generalized Source-Free Domain Adaptation (SSG-SFDA)

Semi-Supervised Generalized Source-Free Domain Adaptation (S...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jiayu An Changming Zhao Dongrui Wu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Continual learning aims to learn on a sequence of new tasks while maintaining the performance on previous tasks. Source-free domain adaptation (SFDA), which adapts a pretrained source model to a target domain, is useful in protecting the source domain data privacy. Generalized SFDA (G-SFDA) combines continual learning and SFDA to achieve outstanding performance on both the source and the target domains. This paper proposes semi-supervised G-SFDA (SSG-SFDA) for domain incremental learning, where a pre-trained source model (instead of the source data), few labeled target data, and plenty of unlabeled target data, are available. The goal is to achieve good performance on all domains. To cope with domain-ID agnostic, SSG-SFDA trains a conditional variational auto-encoder (CVAE) for each domain to learn its feature distribution, and a domain discriminator using virtual shallow features generated by CVAE to estimate the domain ID. To cope with catastrophic forgetting, SSG-SFDA uses soft domain attention to improve the sparse domain attention in G-SFDA. To cope with insufficient labeled target data, SSG-SFDA uses MixMatch to augment the unlabeled target data and better exploit the few labeled target data. Experiments on three datasets demonstrated the effectiveness of SSG-SFDA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression

Integrating Informativeness, Representativeness and Diversit...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziang Liu Dongrui Wu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approach for reducing this data labeling effort. It optimally selects the best few samples to label, so that a better machine learning model can be trained from the same number of labeled samples. This paper considers active learning for regression (ALR) problems. Three essential criteria - informativeness, representativeness, and diversity - have been proposed for ALR. However, very few approaches in the literature have considered all three of them simultaneously. We propose three new ALR approaches, with different strategies for integrating the three criteria. Extensive experiments on 12 datasets in various domains demonstrated their effectiveness.

关键词： Computational modeling Clustering algorithms Machine learning Training Labeling Predictive models image processing

来源：评论

学校读者我要写书评

暂无评论

Tissue P systems with rule production/removal 18th

Tissue P systems with rule production/removal

引用

18th International Conference on Membrane Computing, CMC 1018

作者： Pan, Linqiang Song, Bosheng Zhang, Gexiang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology WuhanHubei430074 China School of Electric and Information Engineering Zhengzhou University of Light Industry ZhengzhouHenan450002 China Robotics Research Center and Key Laboratory of Fluid and Power Machinery Xihua University Chengdu610039 China

ISBN: (纸本)9783319733586

Tissue P systems are computational models inspired by the way of biochemical substance movement/exchange between two cells or between a cell and the environment, where all communication (symport/antiport) rules used in a system are initially set up and keep unchanged during any computation. In this work, a variant of tissue P systems, called tissue P systems with rule production/removal (abbreviated as TRPR P systems) is considered, where rules in a system are dynamically changed during a computation, that is, at any computation step new rules can be produced and some existing rules can be removed. The computation power of TRPR P systems is investigated. It is proved that Turing universality is achieved for TRPR P systems with one cell, and using symport rules of length at most 1, antiport rules of length at most 2 or symport rules of length at most 2 and working in a maximally parallel manner. We further show that TRPR P systems with two cells, using symport rules of length at most 1, and working in a flat maximally parallel manner, are Turing universal. © 2018, Springer International Publishing AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

$H_{\infty}$ Filtering for Neutral Systems With Mixed Delays and Multiplicative Noises

引用

IEEE Transactions on Circuits and Systems II: Express Briefs 2012年第11期59卷 820-824页

作者： Shiping Wen Zhigang Zeng Tingwen Huang Department of Control Science and Engineering Huazhong University of Science and Technology and Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China Texas A & M University at Qatar Doha Qatar

This brief investigates the H ∞ filtering problem for a class of neutral systems with mixed delays and multiplicative noises. The mixed delays comprise both discrete time-varying and distributed delays. Moreover, the multiplicative disturbances are in the form of a scalar Gaussian white noise with unit variance. In the presence of mixed delays and multiplicative noises, sufficient conditions for the existence of an H ∞ filter are derived, such that the filtering error dynamics is asymptotically mean-square stable and also achieves a guaranteed H ∞ performance level. Then, a linear matrix inequality approach for designing such an H ∞ filter is presented. Finally, a numerical example is provided to illustrate the effectiveness of the developed theoretical results.

关键词： Delay Noise Robustness control systems Stochastic systems Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

A protocol for structured illumination microscopy with minimal reconstruction artifacts

引用

生物物理学报 2019年第2期5卷 80-90页

作者： Junchao Fan Xiaoshuai Huang Liuju Li Shan Tan Liangyi Chen Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China School of Automation Huazhong University of Science and Technology Wuhan 430074 China State Key Laboratory of Membrane Biology Beijing Key Laboratory of Cardiometabolic Molecular MedicineInstitute of Molecular Medicine Peking University Beijing 100084 China

The imaging rate of structured illumination microscopy (SIM) reached 188 Hz *** the exposure time decreases,the camera detects fewer virtual photons,while the noise level remains the *** a result,the signal-to-noise ratio (SNR) decreases ***,the SNR decreases further because of photobleaching and *** decreased quality of SIM raw data may lead to surprising artifacts with various causes,which may confuse a new user of SIM *** summarize three significant possible sources of severe artifacts in reconstructed super-resolution (SR) *** motion of a biological sample or an uneven illumination pattern is the most difficult to be *** estimated parameter could also be incorrect,leading to artifact of regular ***,reconstruction with the Wiener method generates stochastic artifacts due to the amplification of noise during the deconvolution *** deal with these problems,we have established a protocol to reconstruct ultrafast SIM raw data obtained in low SNR ***,we checked the quality of the raw data with the imageJ plugin SIMcheck before ***,a modified parameter estimation method was used to improve the precision of the ***,an iterative algorithm was used for SIM reconstruction under low signal-to-noise ratio *** procedure effectively suppressed the artifacts in the super-resolution images reconstructed from raw data of low signal-to-noise ratio.

关键词： Ultrafast SIM Low signal-to-noise ratio Reconstruction

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：