检索结果-内蒙古大学图书馆

Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ding, Zixiang Chen, Yaran Li, Nannan Zhao, Dongbin Chen, C.L. Philip State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Computer Science & Engineering South China University of Technology Guangdong Guangzhou510006 China College of Navigation Dalian Maritime University Dalian116026 China

Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural Network (BCNN), as the search space for amazing efficiency improvement. BCNN reuses the topologies of cells in the convolution block so that BNAS can employ few cells for efficient search. Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology. However, BNAS suffers some drawbacks: 1) insufficient representation diversity for feature fusion and enhancement and 2) time consumption of knowledge embedding design by human experts. This paper proposes Stacked BNAS, whose search space is a developed broad scalable architecture named Stacked BCNN, with better performance than BNAS. On the one hand, Stacked BCNN treats mini BCNN as a basic block to preserve comprehensive representation and deliver powerful feature extraction ability. For multi-scale feature enhancement, each mini BCNN feeds the outputs of deep and broad cells to the enhancement cell. For multi-scale feature fusion, each mini BCNN feeds the outputs of deep, broad and enhancement cells to the output node. On the other hand, Knowledge Embedding Search (KES) is proposed to learn appropriate knowledge embeddings in a differentiable way. Moreover, the basic unit of KES is an over-parameterized knowledge embedding module that consists of all possible candidate knowledge embeddings. Experimental results show that 1) Stacked BNAS obtains better performance than BNAS-v2 on both CIFAR-10 and ImageNet, 2) the proposed KES algorithm contributes to reducing the parameters of the learned architecture with satisfactory performance, and 3) Stacked BNAS delivers a state-of-the-art efficiency of 0.02 GPU days. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

ConnNet: A long-range relation-aware pixel-connectivity network for salient segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Kampffmeyer, Michael Dong, Nanqing Liang, Xiaodan Zhang, Yujia Xing, Eric P. Machine Learning Group UiT The Arctic University of Norway Tromsø9019 Norway Cornell University IthacaNY14850 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Institute of Automation Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100190 China

Salient segmentation aims to segment out attention grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from the utilization of global multi-scale contexts to achieve good local reasoning. Previous works often address it as two-class segmentation problems utilizing complicated multi-step procedures including refinement networks and complex graphical models. We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task. Following the intuition that salient objects can be naturally grouped via semanticaware connectivity between neighboring pixels, we propose a pure Connectivity Net (ConnNet). ConnNet predicts connectivity probabilities of each pixel with its neighboring pixels by leveraging multi-level cascade contexts embedded in the image and long-range pixel relations. We investigate our approach on two tasks, namely salient object segmentation and salient instancelevel segmentation, and illustrate that consistent improvements can be obtained by modeling these tasks as connectivity instead of binary segmentation tasks for a variety of network architectures. We achieve state-of-the-art performance, outperforming or being comparable to existing approaches while reducing inference time due to our less complex approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Pixels

Towards an inclusive Parkinson's screening system

学校读者我要写书评

暂无评论

Towards an inclusive Parkinson's screening system

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Oana Geman Saeid Sanei Iuliana Chiuchisan Adrian Graur Aleš Procházka Oldřich Vyšata Department of Health and Human Development “Stefan eel Mare” University of Suceava Romania Department of Computer Science Electronics and Automation “Stefan cel Mare” University of Suceava Romania Faculty of Engineering and Physical Sciences University of Surrey United Kingdom Department of Computing and Control Engineering Institute of Chemical Technology Czech Republic Department of Neurology Charles University Czech Republic

In this study, brain, and gait dynamic information were combined and used for diagnosis and monitoring of Parkinson's disease (the most important Neurodegenerative Disorder). Analysis of the information corresponding to a prescribed movement involving tremor, and the related changes in brain connectivity is novel and original. Analytically, developing a space-time nonlinear adaptive system which fuses brain and gait information algorithmically is proposed here for the first time. The overall dynamic system will be constrained by the clinical impressions of the patient symptoms embedded in a knowledge-based system. The entire complex constrained problem were solved to enable a powerful model for recognition and monitoring of Parkinson's disease and establishing appropriate rules for its clinical following up.

关键词： Brain modeling Adaptation models Parkinson's disease Chaos Signal processing algorithms Nonlinear dynamical systems

Hierarchical P systems with randomized right-hand sides of rules 18th

学校读者我要写书评

暂无评论

Hierarchical P systems with randomized right-hand sides of r...

18th International Conference on Membrane Computing, CMC 1018

作者： Alhazov, Artiom Freund, Rudolf Ivanov, Sergiu Institute of Mathematics and Computer Science Academy of Sciences of Moldova Academiei 5 Chişinău2028 Moldova Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Wuhan430074 China Faculty of Informatics TU Wien Favoritenstraße 9–11 Vienna1040 Austria LACL Université Paris Est – Créteil Val de Marne 61 av. Général de Gaulle Créteil94010 France TIMC-IMAG/DyCTiM Faculty of Medicine of Grenoble 5 avenue du Grand Sablon La Tronche38700 France

ISBN: (纸本)9783319733586

P systems are a model of hierarchically compartmentalized multiset rewriting. We introduce a novel kind of P systems in which rules are dynamically constructed in each step by non-deterministic pairing of left-hand and right-hand sides. We define three variants of right-hand side randomization and compare each of them with the power of conventional P systems. It turns out that all three variants enable non-cooperative P systems to generate exponential (and thus non-semi-linear) number languages. We also give a binary normal form for one of the variants of P systems with randomized rule right-hand sides. © 2018, Springer International Publishing AG.

关键词： Hierarchical systems

Rethinking development and major research plans of Industrial Internet in China

学校读者我要写书评

暂无评论

Fundamental Research 2024年第1期4卷 3-7页

作者： Chunxiao Jiang Yang Cong Jiming Chen Chenghong Wang Guozheng Wu Ruizhen Zhao Zhiheng Wang Bin Xiao Ting Chen Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China Tsinghua Space Center Tsinghua UniversityBeijing 100084China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China Division III Department of Information SciencesNational Natural Science Foundation of ChinaBeijing 100085China Division II Department of Information SciencesNational Natural Science Foundation of ChinaBeijing 100085China Chongqing Key Laboratory of Image Cognition School of Computer Science and TechnologyChongqing University of Posts and TelecommunicationsChongqing 400065China University of Electronic Science and Technology of China Chengdu 611731China

This paper gives a definition of the Industrial Internet and expounds on the academic connotation of the future Industrial *** this foundation,we outline the development and current status of the Industrial Internet in China and ***,we detail the avant-garde paradigms encompassed within the National Natural Science Foundation of China(NSFC)’s“Future Industrial Internet Fundamental Theory and Key Technologies”research plan and its corresponding management *** research initiative endeavors to enhance interdisciplinary collaborations,aiming for a synergistic alignment of industry,academia,research,and practical *** primary focus of the research plan is on the pivotal scientific challenges inherent to the future industrial *** is poised to traverse the“first mile”,encompassing foundational research and pioneering innovations specific to the industrial internet,and seamlessly bridges to the“last mile”,ensuring the effective commercialization of scientific and technological breakthroughs into tangible industrial market *** anticipated contributions from this initiative are projected to solidify both the theoretical and practical scaffolding essential for the cultivation of a globally competitive industrial internet infrastructure in China.

关键词： Industrial Internet Academic connotation Major research plan Scientific problem Policy advice

Spirometer and sEMG respiratory patterns for clinical decision support system

学校读者我要写书评

暂无评论

Spirometer and sEMG respiratory patterns for clinical decisi...

IEEE Instrumentation and Measurement Technology Conference

作者： Amit Krishan Kumar Mansour H. Assaf Voicu Z. Groza Emil M. Petriu Faculty of Electrical-Electronic Engineering Duy Tan University Da Nang Vietnam Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing Institute of Technology Beijing China School of Information Technology Engineering Mathematics and Physics The University of the South Pacific Suva Republic of Fiji School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

To improve support system for subjects with respiratory ailments, this work analyses the respiratory patterns from spirometer and surface electromyography (sEMG). The patterns are integrated with risk and biochemical systems model to optimise the clinical decision support system (CDSS). The work considers terminal events for the spirometer and sEMG. The events and their associated patterns are correlated and projected on a hyperspace prior implementing it in decision support system. The proposed method shows that the different characteristics of breathing indicate some essential hidden information which when used as 4D scattered projection, optimises the decision making in CDSS. The analysis shows the effectiveness of bimodal respiratory patterns for different breathing capacities, which is promising for the modelled conditions.

关键词：

Development of the System of Initial Excitation of the Autonomous Induction Generator 2nd

学校读者我要写书评

暂无评论

Development of the System of Initial Excitation of the Auton...

2nd Electric Power and Renewable Energy Conference, EPREC 2021

作者： Chenchevoi, Volodymyr Kuznetsov, Valeriy Zachepa, Iurii Chornyi, Oleksii Chencheva, Olga Kuznetsov, Vitaliy Yatsiuk, Rostyslav Luhova, Olha Department of Systems of Automatic Control and Electric Drive Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Kremenchuk Ukraine Electric Power Department Railway Research Institute Chlopickiego str. 50 Warsaw Poland Manufacturing Engineering Department Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Kremenchuk Ukraine Department of the Electrical Engineering and Electromechanic National Metallurgical Academy of Ukraine Gagarina ave. 4 Dnipro Ukraine Department of Automation and Computer-Integrated Technologies Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Kremenchuk Ukraine Department of Electric Machines and Devices Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Kremenchuk Ukraine

ISBN: (纸本)9789811692383

The article defines the conditions of self-excitation of an inductive generator with capacitor excitation as part of an autonomous power source. Recommendations for the design of an autonomous power source based on an asynchronous machine in terms of the implementation of self-excitation conditions and optimal operating modes are formulated. A simulation model of an autonomous inductive generator and a solar battery for the analysis of transient, static and dynamic modes of operation has been developed. The conducted theoretical studies of capacitive self-excitation of inductive machines have created a good basis for solving problems related to the practical use of autonomous sources based on an inductive generator. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Asynchronous generators

Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Chai, Tianyou Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden The Digital Futures Stockholm10044 Sweden The Department of Control Science and Engineering College of Electronics and Information Engineering The Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

This paper considers the distributed online convex optimization problem with time-varying constraints over a network of agents. This is a sequential decision making problem with two sequences of arbitrarily varying convex loss and constraint functions. At each round, each agent selects a decision from the decision set, and then only a portion of the loss function and a coordinate block of the constraint function at this round are privately revealed to this agent. The goal of the network is to minimize the network-wide loss accumulated over time. Two distributed online algorithms with full-information and bandit feedback are proposed. Both dynamic and static network regret bounds are analyzed for the proposed algorithms, and network cumulative constraint violation is used to measure constraint violation, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. In particular, we show that the proposed algorithms achieve O(T max{κ,1-κ}) static network regret and O(T 1-κ/2) network cumulative constraint violation, where T is the time horizon and κ ∈ (0, 1) is a user-defined trade-off parameter. Moreover, if the loss functions are strongly convex, then the static network regret bound can be reduced to O(T κ). Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results. Copyright © 2021, The Authors. All rights reserved.

关键词： Economic and social effects

The learning of fuzzy cognitive maps with noisy data: A rapid and robust learning method with maximum entropy

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Feng, Guoliang Lu, Wei Pedrycz, Witold Yang, Jianhua Liu, Xiaodong School of Control Science and Engineering Dalian University of Technology Dalian116023 China School of Automation Engineering Northeast Electric Power University Jilin132012 China School of Control Science and Engineering Dalian University of Technology Dalian116023 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2V4 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

Numerous learning methods for fuzzy cognitive maps (FCMs), such as the Hebbian-based and the population-based learning methods, have been developed for modeling and simulating dynamic systems. However, these methods are faced with several obvious limitations. Most of these models are extremely time consuming when learning the large-scale FCMs with hundreds of nodes. Furthermore, the FCMs learned by those algorithms lack robustness when the experimental data contain noise. In addition, reasonable distribution of the weights is rarely considered in these algorithms, which could result in the reduction of the performance of the resulting FCM. In this article, a straightforward, rapid, and robust learning method is proposed to learn FCMs from noisy data, especially, to learn large-scale FCMs. The crux of the proposed algorithm is to equivalently transform the learning problem of FCMs to a classic-constrained convex optimization problem in which the least-squares term ensures the robustness of the well-learned FCM and the maximum entropy term regularizes the distribution of the weights of the well-learned FCM. A series of experiments covering two frequently used activation functions (the sigmoid and hyperbolic tangent functions) are performed on both synthetic datasets with noise and real-world datasets. The experimental results show that the proposed method is rapid and robust against data containing noise and that the well-learned weights have better distribution. In addition, the FCMs learned by the proposed method also exhibit superior performance in comparison with the existing methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Fuzzy rules