检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Lin, Mingbao Ji, Rongrong Zhang, Yuxin Zhang, Baochang Wu, Yongjian Tian, Yonghong Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University China School of Automation Science and Electrical Engineering Beihang University China Co. Ltd China School of Electronics Engineering and Computer Science Peking University Beijing China Peng Cheng Laboratory Shenzhen China

Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/ optimization or regularization based on ruleof- thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did. To solve the intractably huge combinations of pruned structure for deep networks, we first propose to shrink the combinations where the preserved channels are limited to a specific space, thus the combinations of pruned structure can be significantly reduced. And then, we formulate the search of optimal pruned structure as an optimization problem and integrate the ABC algorithm to solve it in an automatic manner to lessen human interference. ABCPruner has been demonstrated to be more effective, which also enables the fine-tuning to be conducted efficiently in an end-to-end manner. Experiments on CIFAR-10 show that ABCPruner reduces 73.68% of FLOPs and 88.68% of parameters with even 0.06% accuracy improvement for VGGNet-16. On ILSVRC-2012, it achieves a reduction of 62.87% FLOPs and removes 60.01% of parameters with negligible accuracy cost for ResNet-152. The source codes can be available at https://***/lmbxmu/ABCPruner. 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

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

arXiv

引用

arXiv 2020年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Chai, Tianyou Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden The Department of Electrical Engineering University of North Texas DentonTX76203 United States The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of n local cost functions by using local information exchange is considered. This problem is an important component of many machine learning techniques with data parallelism, such as deep learning and federated learning. We propose a distributed primal–dual stochastic gradient descent (SGD) algorithm, suitable for arbitrarily connected communication networks and any smooth (possibly nonconvex) cost functions. We show that the proposed algorithm achieves the linear speedup convergence rate O(1/√nT) for general nonconvex cost functions and the linear speedup convergence rate O(1/(nT)) when the global cost function satisfies the Polyak–Lojasiewicz (P–L) condition, where T is the total number of iterations. We also show that the output of the proposed algorithm with constant parameters linearly converges to a neighborhood of a global optimum. We demonstrate through numerical experiments the efficiency of our algorithm in comparison with the baseline centralized SGD and recently proposed distributed SGD algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

K-Means Clustering-based Kernel Canonical Correlation Analysis for Multimodal Emotion Recognition ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 10250-10254页

作者： Luefeng Chen Kuanlin Wang Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Wuhan 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6R 2G7 Canada Tokyo Institute of Technology Yokohama 226-8502 Japan

Emotion is an important part of human interaction. Emotional recognition can greatly promote human-centered interaction techniques. On this basis, multimodal feature fusion can effectively improve the emotion recognition rate. However, in the multimodal feature fusion at the feature level, most of the methods do not consider the intrinsic relationship between different modes. Only the fusion of analysis and transformation of the feature matrices of different modes does not make better use of modal differences to improve the recognition rate. This problem led us to propose feature fusion method based on K-Means clustering and kernel canonical correlation analysis (KCCA). Clustering makes the classification of features not classified by mode, but by the degree of influence on emotional labels, thus positively affecting the results of KCCA. The experimental results obtained on the Savee database show that the proposed K-Means based KCCA improves overall classification performance and produces higher recognition rate than that of the state of art methods, such as the Informed Segmentation and Labeling Approach.

关键词： Emotion Recognition K-Means Clustering Kernel Canonical Correlation Analysis Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Seasonal characteristics analysis and uncertainty measurement for wind speed time series

引用

Energy engineering: Journal of the Association of Energy engineering 2020年第5期117卷 289-299页

作者： Deng, Xing Shao, Haijian Wang, Xia School of Computer Science Jiangsu University of Science and Technology Zhenjiang212003 China School of Automation Key Laboratory of Measurement and Control for CSE Ministry of Education Southeast University Nanjing210096 China School of Information Science and Technology Nantong University Nantong226019 China Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore

Wind speed’s distribution nature such as uncertainty and randomness imposes a challenge in high accuracy forecasting. Based on the energy distribution about the extracted amplitude and associated frequency, the uncertainty measurement is processed through Rényi entropy analysis method with time-frequency nat-ure. Nonparametric statistical method is used to test the randomness of wind speed, more precisely, whether or not the wind speed time series is independent and iden-tically distribution (i.i.d) based on the output probability. Seasonal characteristics of wind speed are analyzed based on self-similarity in periodogram under scales range generated by wavelet transformation to reasonably divide the original dataset and effectively reflect the seasonal distribution characteristics. Experimental evaluation based on the dataset from National Renewable Energy laboratory (NREL) is given to demonstrate the performance of the proposed approach. © 2020, Tech Science Press. All rights reserved.

关键词： Wind speed

来源：评论

学校读者我要写书评

暂无评论

Off-Policy Q-Learning for Anti-Interference Control of Multi-Player Systems ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 9189-9194页

作者： Jinna Li Zhenfei Xiao Tianyou Chai Frank. L. Lewis Sarangapani Jagannathan School of Information and Control Engineering Liaoning Shihua University Fushun 113001 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 China UTA Research Institute the University of Texas at Arlington Arlington TX 76118 USA Department of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO 65409 USA

This paper develops a novel off-policy game Q-learning algorithm to solve the anti-interference control problem for discrete-time linear multi-player systems using only data without requiring system matrices to be known. The primary contribution of this paper lies in that the Q-learning strategy employed in the proposed algorithm is implemented in an off-policy policy iteration approach other than on-policy learning due to the well-known advantages of off-policy Q-learning over on-policy Q-learning. All of the players work hard together for the goal of minimizing their common performance index meanwhile defeating the disturbance that tries to maximize the specific performance index, and finally they reach the Nash equilibrium of the game resulting in satisfying disturbance attenuation condition. In order to find the solution to the Nash equilibrium, the anti-interference control problem is first transformed into an optimal control problem. Then an off-policy Q-learning algorithm is proposed in the framework of typical adaptive dynamic programming (ADP) and game architecture, such that control policies of all players can be learned using only measured data. Comparative simulation results are provided to verify the effectiveness of the proposed method.

关键词： H ∞ control off-policy Q-learning game theory Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Asymmetric CNN for image super-resolution

arXiv

引用

arXiv 2021年

作者： Tian, Chunwei Xu, Yong Zuo, Wangmeng Lin, Chia-Wen Zhang, David The Bio-Computing Research Center Harbin Institute of Technology ShenzhenShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition ShenzhenGuangdong518055 China The School of Computer Science and Technology Harbin Institute of Technology HarbinHeilongjiang150001 China The Peng Cheng Laboratory ShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen Guangdong518055 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan ShenzhenGuangdong518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. However, customized architectures gather different features via treating all pixel points as equal to improve the performance of given application, which ignores the effects of local power pixel points and results in low training efficiency. In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. The AB utilizes one-dimensional asymmetric convolutions to intensify the square convolution kernels in horizontal and vertical directions for promoting the influences of local salient features for SISR. The MEB fuses all hierarchical low-frequency features from the AB via residual learning (RL) technique to resolve the long-term dependency problem and transforms obtained low-frequency features into high-frequency features. The HFFEB exploits low- and high-frequency features to obtain more robust super-resolution features and address excessive feature enhancement problem. Additionally, it also takes charge of reconstructing a high-resolution (HR) image. Extensive experiments show that our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems. The code of the ACNet is shown at https://***/hellloxiaotian/ACNet. © 2021, CC BY-NC-ND.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Many-body Hilbert space scarring on a superconducting processor

arXiv

引用

arXiv 2022年

作者： Zhang, Pengfei Dong, Hang Gao, Yu Zhao, Liangtian Hao, Jie Desaules, Jean-Yves Guo, Qiujiang Chen, Jiachen Deng, Jinfeng Liu, Bobo Ren, Wenhui Yao, Yunyan Zhang, Xu Xu, Shibo Wang, Ke Jin, Feitong Zhu, Xuhao Zhang, Bing Li, Hekang Song, Chao Wang, Zhen Liu, Fangli Papić, Zlatko Ying, Lei Wang, H. Lai, Ying-Cheng Department of Physics ZJU-Hangzhou Global Scientific and Technological Innovation Center Interdisciplinary Center for Quantum Information Zhejiang Province Key Laboratory of Quantum Technology and Device Zhejiang University Hangzhou310027 China Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Physics and Astronomy University of Leeds LeedsLS2 9JT United Kingdom Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies Hangzhou310027 China QuEra Computing Inc. BostonMA02135 United States School of Electrical Computer and Energy Engineering Department of Physics Arizona State University TempeAZ85287 United States

Quantum many-body scarring (QMBS) – a recently discovered form of weak ergodicity breaking in strongly-interacting quantum systems – presents opportunities for mitigating thermalization-induced decoherence in quantum information processsing. However, the existing experimental realizations of QMBS are based on kinetically-constrained systems where an emergent dynamical symmetry "shields" such states from the thermalizing bulk of the spectrum. Here, we experimentally realize a distinct kind of QMBS phenomena by approximately decoupling a part of the many-body Hilbert space in the computational basis. Utilizing a programmable superconducting processor with 30 qubits and tunable couplings, we realize Hilbert space scarring in a non-constrained model in different geometries, including a linear chain as well as a quasi-one-dimensional comb geometry. By performing full quantum state tomography on 4-qubit subsystems, we provide strong evidence for QMBS states by measuring qubit population dynamics, quantum fidelity and entanglement entropy following a quench from initial product states. Our experimental findings broaden the realm of QMBS mechanisms and pave the way to exploiting correlations in QMBS states for applications in quantum information technology. Copyright © 2022, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Automating Surgical Peg Transfer: Calibration with Deep Learning Can Exceed Speed, Accuracy, and Consistency of Humans

arXiv

引用

arXiv 2020年

作者： Hwang, Minho Ichnowski, Jeff Thananjeyan, Brijen Seita, Daniel Paradis, Samuel Fer, Danyal Low, Thomas Goldberg, Ken Daegu Korea Republic of The Department of Electrical Engineering and Computer Sciences University of California Berkeley United States The Department of General Surgery University of California San Francisco East Bay OaklandCA94602 United States The Robotics Laboratory Sri International Menlo ParkCA94025 United States

Peg transfer is a well-known surgical training task in the Fundamentals of Laparoscopic Surgery (FLS). While human surgeons teleoperate robots such as the da Vinci to perform this task with high speed and accuracy, it is challenging to automate. This paper presents a novel system and control method using a da Vinci Research Kit (dVRK) surgical robot and a Zivid depth sensor, and a human subjects study comparing performance on three variants of the peg-transfer task: unilateral, bilateral without handovers, and bilateral with handovers. The system combines 3D printing, depth sensing, and deep learning for calibration with a new analytic inverse kinematics model and time-minimized motion controller. In a controlled study of 3384 peg transfer trials performed by the system, an expert surgical resident, and 9 volunteers, results suggest that the system achieves accuracy on par with the experienced surgical resident and is significantly faster and more consistent than the surgical resident and volunteers. The system also exhibits the highest consistency and lowest collision rate. To our knowledge, this is the first autonomous system to achieve "superhuman" performance on a standardized surgical task. All data is available at https://***/view/surgicalpegtransfer. Copyright © 2020, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Set stability for switched Boolean networks with open-loop and closed-loop switching signals

引用

Science China(Information Sciences) 2018年第9期61卷 232-240页

作者： Xiaohua LI Jianquan LU Jianlong QIU Xiangyong CHEN Xiaodi LI Fuad E.ALSAADI School of Automation and Engineering and Key Laboratory of Complex Systems and Intelligent Computing in Universities of Shandong Linyi University School of Mathematics and Statistics Shandong Normal University School of Mathematics Southeast University Department of Electrical and Computer Engineering King Abdulaziz University

This paper mainly analyzes the set stability of switched Boolean networks(SBNs) by considering two different methods of switching signals in the form of open-loop and closed-loop switching. First, the definitions of set stability are proposed for SBNs with such switching signals. Then, we propose two different algorithms to find the largest open-loop switching invariant set and largest closed-loop switching invariant set. Furthermore, the corresponding set stability conditions for SBNs are given in each case. In addition,the constructive procedures are presented to design the switching signal sequence to achieve set stability under the two different methods of switching signals. Finally, the effectiveness of the proposed algorithms and research results are demonstrated using two numerical examples.

关键词： switched Boolean network set stability semi-tensor product switching signal design

来源：评论

学校读者我要写书评

暂无评论

Robust lane marking detection algorithm using drivable area segmentation and extended SLT

Robust lane marking detection algorithm using drivable area ...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Ozgunalp, Umar Liu, Ming Fan, Rui Cheng, Shanshan Sun, Yuxiang Zuo, Weixun Zhu, Yilong Xue, Bohuan Zheng, Linwei Liang, Qing Cyprus International University Electrical and Electronics Engineering North Cyprus Turkey Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hangzhou ATG Intelligent Technology Co. Ltd. Hangzhou China Guolu Gaoke Engineering Technology Institute Co. Ltd. Beijing China Robotics Institute Hong Kong University of Science and Technology Robotics and Multiperception Laboratory Hong Kong

ISBN: (纸本)9781728163215

In this paper, a robust lane detection algorithm is proposed, where the vertical road profile of the road is estimated using dynamic programming from the v-disparity map and, based on the estimated profile, the road area is segmented. Since the lane markings are on the road area and any feature point above the ground will be a noise source for the lane detection, a mask is created for the road area to remove some of the noise for lane detection. The estimated mask is multiplied by the lane feature map in a bird's eye view (BEV). The lane feature points are extracted by using an extended version of symmetrical local threshold (SLT), which not only considers dark light dark transition (DLD) of the lane markings, like (SLT), but also considers parallelism on the lane marking borders. The segmentation then uses only the feature points that are on the road area. A maximum of two linear lane markings are detected using an efficient 1D Hough transform. Then, the detected linear lane markings are used to create a region of interest (ROI) for parabolic lane detection. Finally, based on the estimated region of interest, parabolic lane models are fitted using robust fitting. Due to the robust lane feature extraction and road area segmentation, the proposed algorithm robustly detects lane markings and achieves lane marking detection with an accuracy of 91% when tested on a sequence from the KITTI dataset. © 2019 IEEE.

关键词： Hough transforms

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：