检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Ming Sonoda, Sho Cao, Feilong Wang, Yu Guang Liang, Jiye Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University Jinhua China Deep Learning Theory Team RIKEN AIP Tokyo Japan College of Sciences China Jiliang University Hangzhou China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Taiyuan China

We investigate the expressive power of depth-2 bandlimited random neural networks. A random net is a neural network where the hidden layer parameters are frozen with random assignment, and only the output layer parameters are trained by loss minimization. Using random weights for a hidden layer is an effective method to avoid non-convex optimization in standard gradient descent learning. It has also been adopted in recent deep learning theories. Despite the well-known fact that a neural network is a universal approximator, in this study, we mathematically show that when hidden parameters are distributed in a bounded domain, the network may not achieve zero approximation error. In particular, we derive a new nontrivial approximation error lower bound. The proof utilizes the technique of ridgelet analysis, a harmonic analysis method designed for neural networks. This method is inspired by fundamental principles in classical signal processing, specifically the idea that signals with limited bandwidth may not always be able to perfectly reconstruct the original signal. We corroborate our theoretical results with various simulation studies, and generally, two main take-home messages are offered: (i) Not any distribution for selecting random weights is feasible to build a universal approximator;(ii) A suitable assignment of random weights exists but to some degree is associated with the complexity of the target function. © 2020, CC BY.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Review and prospect: Deep learning in nuclear magnetic resonance spectroscopy

arXiv

引用

arXiv 2020年

作者： Chen, Dicheng Wang, Zi Guo, Di Orekhov, Vladislav Qu, Xiaobo Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance State Key Laboratory of Physical Chemistry of Solid Surfaces Xiamen University P.O.Box 979 Xiamen361005 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Department of Chemistry and Molecular Biology University of Gothenburg Box 465 Gothenburg40530 Sweden

Since the concept of Deep Learning (DL) was formally proposed in 2006, it had a major impact on academic research and industry. Nowadays, DL provides an unprecedented way to analyze and process data with demonstrated great results in computer vision, medical imaging, natural language processing, etc. In this Minireview, we summarize applications of DL in Nuclear Magnetic Resonance (NMR) spectroscopy and outline a perspective for DL as entirely new approaches that are likely to transform NMR spectroscopy into a much more efficient and powerful technique in chemistry and life science. Copyright © 2020, The Authors. All rights reserved.

关键词： Nuclear magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Intelligent spectrum learning for wireless networks with reconfigurable intelligent surfaces

arXiv

引用

arXiv 2021年

作者： Yang, Bo Cao, Xuelin Huang, Chongwen Yuen, Chau Qian, Lijun Renzo, Marco Di Engineering Product Development Pillar Singapore University of Technology and Design Singapore487372 Singapore Zhejiang Provincial Key Lab of information processing communication and networking Zhejiang University No.38 Zheda Road Hangzhou310007 China Department of Electrical and Computer Engineering CREDIT Center Prairie View A&M University Texas A&M University System Prairie ViewTX77446 United States Université Paris-Saclay CNRS CentraleSupélec Laboratoire des Signaux et Systèmes 3 Rue Joliot-Curie Gif-sur-Yvette91192 France

Reconfigurable intelligent surface (RIS) has become a promising technology for enhancing the reliability of wireless communications, which is capable of reflecting the desired signals through appropriate phase shifts. However, the intended signals that impinge upon an RIS are often mixed with interfering signals, which are usually dynamic and unknown. In particular, the received signal-to-interference-plus-noise ratio (SINR) may be degraded by the signals reflected from the RISs that originate from non-intended users. To tackle this issue, we introduce the concept of intelligent spectrum learning (ISL), which uses an appropriately trained convolutional neural network (CNN) at the RIS controller to help the RISs infer the interfering signals directly from the incident signals. By capitalizing on the ISL, a distributed control algorithm is proposed to maximize the received SINR by dynamically configuring the active/inactive binary status of the RIS elements. Simulation results validate the performance improvement offered by deep learning and demonstrate the superiority of the proposed ISL-aided approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Topic-Triggered Translation Model for Statistical Machine Translation

引用

Chinese Journal of Electronics 2017年第1期26卷 65-72页

作者： SU Jinsong WANG Zhihao WU Qingqiang YAO Junfeng LONG Fei ZHANG Haiying Software School Xiamen University Provincial Key Laboratory for Computer Information Processing Technology Soochow University Automation Department Xiamen University

Translation model containing translation rules with probabilities plays a crucial role in statistical machine translation. Conventional method estimates translation probabilities with only the consideration of cooccurrence frequencies of bilingual translation units, while ignoring document-level context information. In this paper, we extend the conventional translation model to a topic-triggered one. Specifically, we estimate topic-specific translation probabilities of translation rules by leveraging topical context information, and online score selected translation rules according to topic posterior distributions of translated sentences. As compared with the conventional model, our model allows for more fine-grained distinction among different translations. Experiment results on large data set demonstrate the effectiveness of our model.

关键词： Statistical machine translation Topictriggered translation model Topical context information

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Domain Adaptation via Variational Inference for Evolving Concept Drift

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Wang, Chuang Wang, Zidong Sheng, Weiguo Liu, Qingqiang Dong, Hongli Northeast Petroleum University Artificial Intelligence Energy Research Institute Daqing163318 China Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China Northeast Petroleum University Sanya Offshore Oil & Gas Research Institute Sanya572025 China Brunel University London Department of Computer Science Middlesex UxbridgeUB8 3PH United Kingdom Hangzhou Normal University School of Information Science and Technology Hangzhou311121 China Northeast Petroleum University School of Electrical & Information Engineering Daqing163318 China

The concept of fuzzy domain adaptation (FDA) isfocused on transferring a model trained in a source domainto a target domain, where intrinsic distribution discrepanciesexist in non-stationary and non-deterministic environments. Inthis paper, a novel drift decoupling-based variational adaptationnetwork (DD-VAN) is proposed for FDA, allowing for the learningof intra-domain evolutionary patterns and inter-domain uncer-tainties. The DD-VAN algorithm is implemented in three mainsteps: (1) an intra-domain evolutionary trend modeling module isfirst employed to capture unknown temporal variations throughan autoencoder architecture with variational inference;(2) aprototype-assisted fuzzy clustering module is used to estimate themembership degree of the target data, characterizing the inherentuncertainty and imprecision present in real-world distributions;and (3) a membership-aware domain fuzzy matching module isutilized to learn the gradual transitions between category-relateddata pairs in the source and target domains by introducing un-certainties. Furthermore, it is theoretically demonstrated that theinferred posterior distributions of latent codes can be optimizedto align with the corresponding prior distributions by minimizingthe Kullback-Leibler divergence. Extensive experiments are con-ducted on cross-domain tasks involving both synthetic and real-world datasets, and the experimental results suggest that the DD-VAN algorithm outperforms existing state-of-the-art methods. © 1993-2012 IEEE.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Adaptive Clustering SOFC Image Segmentation Based on Particle Swarm Optimization

Adaptive Clustering SOFC Image Segmentation Based on Particl...

引用

2019 3rd International Conference on Machine Vision and information technology (CMVIT 2019)

作者： Xuefei Yang Xiaowei Fu Xi Li College of Computer Science and Technology Wuhan University of Science and TechnologyHubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System State Key Laboratory of Materials Processing and Die & Mould Technology Huazhong University of Science and Technology College of Automation Huazhong University of Science and Technology

Microstructural parameters are important for analyzing the chemistry and performance of solid oxide fuel cells（SOFCs）. Aiming at the YSZ/Ni anode optical microscopy（OM） image of SOFC, in this paper, particle swarm intelligent optimization algorithm is used to improve the fuzzy C-means clustering algorithm for image segmentation. Particle swarm optimization is used to adaptively search the initial clustering center, helping to avoid local optimization and preserve more image detail. The experimental results show that the proposed method can improve the segmentation accuracy of images. At the same time, it can accurately segment the SOFC three-phase and provide effective image segmentation results for the microstructure parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face Analysis for Coronary Heart Disease Diagnosis 12

Face Analysis for Coronary Heart Disease Diagnosis

引用

12th International Congress on Image and Signal processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

作者： Lin, Shisong Zhuang, Xiaodong Huang, Shiyun Liu, Yahui Shen, Linlin Liao, Xinxue Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Cardiology department First affiliated hospital of Sun Yat-sen University Guangzhou China NHC Key Laboratory of Assisted Circulation Sun Yat-sen University Guangzhou China Shenzhen National Medical Science and Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9781728148526

CHD (Coronary Heart Disease) is one of the leading causes of cardiovascular disease deaths. Invasive coronary arteriography is one of the widely used approaches to diagnose CHD. However, the time cost and expenses for most of the diagnosis methodologies are high and some patients are reluctant to do such a diagnosis. In this paper, we aim to develop a novel low cost method to predict CHD. As suggested by the cardiologists, there are substantial differences between the facial images of patients with CHD and those of healthy subjects. In this paper, we conduct an automatic analysis of the texture features extracted from eight ROIs (Regions of Interests) of the face images. Based on the texture features, random forest and decision tree are used to predict whether the subject has a CHD, or not. The experimental results on a set of 1528 face images collected from 309 subjects suggest that, our approach achieved a promising, i.e. 72.73%, prediction accuracy. © 2019 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A monaural speech enhancement method for robust small-footprint keyword spotting

arXiv

引用

arXiv 2019年

作者： Gu, Yue Du, Zhihao Zhang, Hui Zhang, Xueliang Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Inner Mongolia University Hohhot China School of Computer Science and Technology Harbin Institute of Technology Harbin China

Robustness against noise is critical for keyword spotting (KWS) in real-world environments. To improve the robustness, a speech enhancement front-end is involved. Instead of treating the speech enhancement as a separated preprocessing before the KWS system, in this study, a pre-trained speech enhancement front-end and a convolutional neural networks (CNNs) based KWS system are concatenated, where a feature transformation block is used to transform the output from the enhancement front-end into the KWS system's input. The whole model is trained jointly, thus the linguistic and other useful information from the KWS system can be back-propagated to the enhancement front-end to improve its performance. To fit the small-footprint device, a novel convolution recurrent network is proposed, which needs fewer parameters and computation and does not degrade performance. Furthermore, by changing the input features from the power spectrogram to Mel-spectrogram, less computation and better performance are obtained. our experimental results demonstrate that the proposed method significantly improves the KWS system with respect to noise robustness. Copyright © 2019, The Authors. All rights reserved.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Dynamic maintenance of decision rules for decision attribute values’ changing 25th

Dynamic maintenance of decision rules for decision attribute...

引用

25th International Conference on Neural information processing, ICONIP 2018

作者： Wang, Yingyao Dai, Jianhua Shi, Hong School of Computer Science and Technology Tianjin University Tianjin300350 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha410081 China

ISBN: (纸本)9783030041816

Rule induction method based on rough set theory (RST) which can generate a minimal set of decision rules by using attribute reduction and approximations has received much attention recently. In real-life, the variation of objects, attributes and attributes’ values affects reducts and approximations, e.g., the coarsening and refining of attributes’ values. The goal of this paper is dynamic maintenance of decision rules for decision attribute values’ coarsening and refining. Two incremental rough-set based methods are proposed to deal with this issue by updating assignment discernibility matrix dynamically without recomputing the reducts from the beginning, which increases the efficiency. © Springer Nature Switzerland AG 2018.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Incentive Announcement System for Internet of Vehicles

Blockchain-Based Incentive Announcement System for Internet ...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yang Yang Jialiang Chen Xianghan Zheng Ximeng Liu Wenzhong Guo Hairong Lv College of Mathematics and Computer Science Fuzhou University Fuzhou China Guangxi Key Laboratory of Cryptography and Information Security Guangnxi China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) Fuzhou China Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division and Center for Synthetic and Systems Biology Beijing National Research Center for Information Science and TechnologyDepartment of Automation Tsinghua University Beijing China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

With the rapid development of computation and communication technologies, the traditional vehicle ad hoc networks (VANETs) are changing to Internet of vehicle (IoV). Vehicular announcement networks in IoV have been widely used in the communication of vehicles. Generally, we need to solve two problems while establishing a vehicular announcement system. First, we need to protect user's privacy when broadcasting the message. Second, participants usually lack the enthusiasm to reply to the announcement. To solve these two problems, we propose a novel blockchain-based incentive announcement system that not only allows participants to anonymously announce their message on the blockchain in a non-trusted environment, but also motivates witnesses to respond to the request of the traffic information with incentive mechanism. Meanwhile, traffic messages and signatures in our system are tamper-resistant, which are recorded on the blockchain. According to the security and performance analysis, it shows that our system is privacy-preserving and efficient in computation cost.

关键词： Blockchain Privacy Smart contracts Authentication Internet Remuneration Hash functions

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：