检索结果-内蒙古大学图书馆

Multi-view hybrid embedding: A divide-and-conquer approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xu, Jiamiao Yu, Shujian You, Xinge Leng, Mengjun Jing, Xiao-Yuan Chen, C. L. Philip School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Department of Computer Science University of Houston HoustonTX77204 United States State Key Laboratory of Software Engineering School of Computer Wuhan University China Department of Computer and Information Science Faculty of Science and Technology University of Macau Macau99999 China Dalian Maritime University Dalian116026 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multiview subspace learning (MvSL) that aims to learn a latent subspace shared by multi-view data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multi-view data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divideand-Conquer strategy, we propose Multi-view Hybrid Embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase discriminability in intra-view and interview samples respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate overwhelming advantages against the stateof-the-art MvSL based cross-view classification approaches in terms of classification accuracy and robustness. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

control 5.0: From Newton to Merton in Popper's Cyber-Social-Physical Spaces

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2016年第3期3卷 233-234页

作者： Fei-Yue Wang IEEE State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences (SKL-MCCS CASIA) Research Center of Computational Experiments and Parallel Systems The National University of Defense Technology

The future of control in cyberspace of parallel worlds is discussed. It argues for the coming age of control 5.0,the control technology for the new IT capable of dealing with artificial worlds with VR, AR, AI and robotics. The discipline of automation needs a new interpretation of its core knowledge and skill set of modeling, analysis, and control for cyber-socialphysical systems, and a paradigm shift from Newtonian systems with Newton's Laws or Big Laws with Small Data to Mertonian systems with Merton's Laws or Small Laws with Big Data.

关键词： control 5.0 parallel control knowledge automation CPS CSP CPSS Merton Wiener Popper

New advances in complex motion control for single robot systems and multi-agent systems

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2016年第12期59卷 1963-1964页

作者： FANG Hao LU Shao Lei CHEN Jie School of Automation Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081China

CHEN Jie,email：chenjie@***

关键词： robot advances email cooperation simplified decomposed scenarios classic climbing obstacles

Long short-term memory based on a reward/punishment strategy for recurrent neural networks

学校读者我要写书评

暂无评论

Long short-term memory based on a reward/punishment strategy...

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Jiangjiang Liu Biao Luo Pengfei Yan Ding Wang Derong Liu School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781538629024

Recurrent neural networks and their variants have received huge success in many difficult tasks, such as handwriting recognition and generation, natural language processing, acoustic modeling of speech, and so on. As a kind of recurrent neural network architectures, the long short-term memory (LSTM) has attracted great attention. Most research works focus on its structures, training algorithms and topology structures. As an improvement to the structure of LSTM, a reward/punishment strategy is developed for LSTM in this paper, which we call RP-LSTM. In RP-LSTM, a reward/punishment (RP) strategy is proposed to evaluate its memory cells' memorization such that it improves its efficiency by forgetting more reasonably. Analysis of properties of the developed RP-LSTM is conducted from the neuroscience aspect. To test the performance of the developed RP-LSTM, comparative simulation studies are conducted on three structures, i.e., LSTM, LSTM with forget gate (LSTM-FG) and RP-LSTM. Simulation results on sentiment analysis model and sequence to sequence model demonstrate that RP-LSTM achieves better performance.

关键词： Logic gates Mathematical model Training Memory management Recurrent neural networks Speech Neuroscience

DeepTrend: A deep hierarchical neural network for traffic flow prediction

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Dai, Xingyuan Fu, Rui Lin, Yilun Li, Li Wang, Fei-Yue State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Department of Automation Tsinghua University Beijing100084 China

In this paper, we consider the temporal pattern in traffic flow time series, and implement a deep learning model for traffic flow prediction. Detrending based methods decompose original flow series into trend and residual series, in which trend describes the fixed temporal pattern in traffic flow and residual series is used for prediction. Inspired by the detrending method, we propose DeepTrend, a deep hierarchical neural network used for traffic flow prediction which considers and extracts the time-variant trend. DeepTrend has two stacked layers: extraction layer and prediction layer. Extraction layer, a fully connected layer, is used to extract the time-variant trend in traffic flow by feeding the original flow series concatenated with corresponding simple average trend series. Prediction layer, an LSTM layer, is used to make flow prediction by feeding the obtained trend from the output of extraction layer and calculated residual series. To make the model more effective, DeepTrend needs first pre-trained layer-by-layer and then fine-tuned in the entire network. Experiments show that DeepTrend can noticeably boost the prediction performance compared with some traditional prediction models and LSTM with detrending based methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Forecasting

Compressive phase retrieval via reweighted amplitude flow

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhang, Liang Wang, Gang Giannakis, Georgios B. Chen, Jie Digital Technology Center Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China School of Automation State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

The problem of reconstructing a sparse signal vector from magnitude-only measurements (a.k.a., compressive phase retrieval), emerges naturally in diverse applications, but it is NP-hard in general. Building on recent advances in nonconvex optimization, this paper puts forth a new algorithm that is termed compressive reweighted amplitude flow and abbreviated as CRAF, for compressive phase retrieval. Specifically, CRAF operates in two stages. The first stage seeks a sparse initial guess via a new spectral procedure. In the second stage, CRAF implements a few hard thresholding based iterations using reweighted gradients. When there are sufficient measurements, CRAF provably recovers the underlying signal vector exactly with high probability under suitable conditions. Moreover, its sample complexity coincides with that of the state-of-the-art procedures. Finally, substantial simulated tests showcase remarkable performance of the new spectral initialization, as well as improved exact recovery relative to competing alternatives. Copyright © 2017, The Authors. All rights reserved.

关键词： Iterative methods

ExNa: an efficient search pattern for semantic search engines

学校读者我要写书评

暂无评论

ExNa: an efficient search pattern for semantic search engine...

作者： Wei, Xiao Zeng, Daniel Dajun State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Shanghai Institute of Technology Shanghai China

Recent years have witnessed the emergence of new types of semantic search engines which attempt to overcome the defects of the traditional search engines by providing different search patterns. A big question here is that in order to achieve the semantic search engines (SSEs), what type(s) of search patterns should SSEs support? To help seek one of the many possible answers, in this paper we start with classifying and comparing current search engines, particularly from the perspective of search patterns which consist of index structure, user profiles, and interaction mechanism. We then present a novel search pattern named ExNa by defining its model and basic operations in detail. To validate the ExNa search pattern, we develop a prototype search engine named KNOWLE, and the experimental results show that KNOWLE equipped with ExNa can improve both the efficiency of the entire system when compared with search engines of other search patterns. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

关键词： Big data

Towards quality advancement of underwater machine vision with generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Chen, Xingyu Yu, Junzhi Kong, Shihan Wu, Zhengxing Fang, Xi Wen, Li University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Mechanical Engineering and Automation Beihang University Beijing100191 China

Underwater machine vision has attracted significant attention, but its low quality has prevented it from a wide range of applications. Although many different algorithms have been developed to solve this problem, real-time adaptive methods are frequently deficient. In this paper, based on filtering and the use of generative adversarial networks (GANs), two approaches are proposed for the aforementioned issue, i.e., a filteringbased restoration scheme (FRS) and a GAN-based restoration scheme (GAN-RS). Distinct from previous methods, FRS restores underwater images in the Fourier domain, which is composed of a parameter search, filtering, and enhancement. Aiming to further improve the image quality, GAN-RS can adaptively restore underwater machine vision in real time without the need for pretreatment. In particular, information in the Lab color space and the dark channel is developed as loss functions, namely, underwater index loss and dark channel prior loss, respectively. More specifically, learning from the underwater index, the discriminator is equipped with a carefully crafted underwater branch to predict the underwater probability of an image. A multi-stage loss strategy is then developed to guarantee the effective training of GANs. Through extensive comparisons on the image quality and applications, the superiority of the proposed approaches is confirmed. Consequently, the GAN-RS is considerably faster and achieves a state-of-the-art performance in terms of the color correction, contrast stretch, dehazing, and feature restoration of various underwater scenes. The source code will be made available. Copyright © 2017, The Authors. All rights reserved.

关键词： Image reconstruction

Data-Based Robust control for Unknown Nonlinear systems 35

学校读者我要写书评

暂无评论

Data-Based Robust Control for Unknown Nonlinear Systems

第35届中国控制会议

作者： YANG Xiong LIU Derong WEI Qinglai School of Electrical Engineering and Automation Tianjin University School of Automation and Electrical Engineering University of Science and Technology Beijing The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781509009107

In this paper, we develop a data-based robust control method for a class of unknown nonlinear systems with input constraints. First, we transform the robust control problem into a constrained optimal control problem by introducing a value function for the nominal system. Then, under the framework of integral reinforcement learning, we construct an actor-critic architecture to approximately solve the constrained optimal control problem. Based on the present architecture, we only require system data rather than the availability of full/partial prior knowledge of system dynamics. In addition, by using Lyapunov's direct method, we prove that the obtained approximate optimal control can guarantee the unknown nonlinear system to be uniformly ultimately bounded. Finally, we provide an example to illustrate the effectiveness of the developed method.

关键词： Constrained input Integral reinforcement learning Nonlinear systems Optimal control Robust control