检索结果-内蒙古大学图书馆

Type-Aware Question Answering over knowledge Base with Attention-Based Tree-Structured Neural Networks

Journal of Computer Science & Technology 2017年第4期32卷 805-813页

作者： Jun Yin Wayne Xin Zhao Xiao-Ming Li School of Electronic Engineering and Computer Science Peking University Beijing 100871 China School of Information Renmin University of China Beijing 100872 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou 510006 China

Question answering (QA) over knowledge base (KB) aims to provide a structured answer from a knowledge base to a natural language question. In this task, a key step is how to represent and understand the natural language query. In this paper, we propose to use tree-structured neural networks constructed based on the constituency tree to model natural language queries. We identify an interesting observation in the constituency tree: different constituents have their own semantic characteristics and might be suitable to solve different subtasks in a QA system. Based on this point, we incorporate the type information as an auxiliary supervision signal to improve the QA performance. We call our approach type-aware QA. We jointly characterize both the answer and its answer type in a unified neural network model with the attention mechanism. Instead of simply using the root representation, we represent the query by combining the representations of different constituents using task-specific attention weights. Extensive experiments on public datasets have demonstrated the effectiveness of our proposed model. More specially, the learned attention weights are quite useful in understanding the query. The produced representations for intermediate nodes can be used for analyzing the effectiveness of components in a QA system.

关键词： question answering deep neural network knowledge base

来源：评论

学校读者我要写书评

暂无评论

Weighted Feature Pyramid Networks for Object Detection

Weighted Feature Pyramid Networks for Object Detection

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Xiaohan Li Taotao Lai Shuaiyu Wang Quan Chen Changcai Yang Riqing Chen Jinxun Lin Fu Zheng Digital Fujian Institute of Big Data for Agriculture and Forestry College of Computer and information Sciences Fujian Agriculture and Forestry University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China Fu Jian Shu Bo Xun Information Technology Co. Ltd

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Feature Pyramid Networks (FPN) is a popular feature extraction. However, FPN and its variants do not investigate the influence of resolution information and semantic information in the object detection. Thus, FPN and its variants cannot detect some objects on challenging images. In this paper, based on FPN, we propose to use gaussian kernel function to assign different weight values to semantic information and resolution information for different images in the object detection. The proposed method, is called a Weighted Feature Pyramid Network (WFPN), and shows significant improvement over the traditional feature pyramids in several applications. Using WFPN in Faster R-CNN system, the proposed method achieves better performance on the PASCAL detection benchmark.

关键词： Feature extraction Kernel Object detection Agriculture Forestry Semantics big data

来源：评论

学校读者我要写书评

暂无评论

ESL-SELO:A Robust Image Denoising Algorithm with Penalty

引用

Acta Mathematicae Applicatae Sinica 2017年第3期33卷 753-770页

作者： Guo-hua WANG San-guo ZHANG Peng-jie DAI School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing100049China School of Business Remin University of ChinaBeijing 100872China

Robust image recovery methods have been attracted more and more attention in recent decades for its good property of tolerating system errors or measuring noise. In this paper, we propose a new robust method （ESL-SELO） to recover nosing image, which combine exponential loss function and seamless-L0 （SELO） penalty function to guarantee both accuracy and robustness of the estimator. Theoretical result showed that our method has a local optimal solution and good asymptotic properties. Finally, we compare our method with other methods in simulation which shows better robustness and takes much less time.

关键词： denoising algorithm penalty function robust SELO

来源：评论

学校读者我要写书评

暂无评论

Attentional Neural Fields for Crowd Counting

Attentional Neural Fields for Crowd Counting

引用

International Conference on Computer Vision (ICCV)

作者： Anran Zhang Lei Yue Jiayi Shen Fan Zhu Xiantong Zhen Xianbin Cao Ling Shao School of Electronic and Information Engineering Beihang University Beijing China Inception Institute of Artificial Intelligence Abu Dhabi UAE Ministry of Industry and Information Technology of China Key Laboratory of Advanced Technology of Near Space Information System (Beihang University) Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beijing China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Crowd counting has recently generated huge popularity in computer vision, and is extremely challenging due to the huge scale variations of objects. In this paper, we propose the Attentional Neural Field (ANF) for crowd counting via density estimation. Within the encoder-decoder network, we introduce conditional random fields (CRFs) to aggregate multi-scale features, which can build more informative representations. To better model pair-wise potentials in CRFs, we incorperate non-local attention mechanism implemented as inter- and intra-layer attentions to expand the receptive field to the entire image respectively within the same layer and across different layers, which captures long-range dependencies to conquer huge scale variations. The CRFs coupled with the attention mechanism are seamlessly integrated into the encoder-decoder network, establishing an ANF that can be optimized end-to-end by back propagation. We conduct extensive experiments on four public datasets, including ShanghaiTech, WorldEXPO 10, UCF-CC-50 and UCF-QNRF. The results show that our ANF achieves high counting performance, surpassing most previous methods.

关键词： Estimation Task analysis Feature extraction Computational modeling Adaptation models Aggregates Machine learning

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Loss of grand histone H3 lysine 27 trimethylation domains mediated transcriptional activation in esophageal squamous cell carcinoma

引用

NPJ genomic medicine 2021年第1期6卷 79页

作者： Jian Yuan Qi Jiang Tongyang Gong Dandan Fan Ji Zhang Fukun Chen Xiaolin Zhu Xinyu Wang Yunbo Qiao Hongyan Chen Zhihua Liu Jianzhong Su School of Biomedical Engineering School of Ophthalmology & Optometry and Eye Hospital Wenzhou Medical University Wenzhou China. Institute of Biomedical Big Data Wenzhou Medical University Wenzhou China. State Key Laboratory of Molecular Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China. Precise Genome Engineering Center School of Life Sciences Guangzhou University Guangzhou China. State Key Laboratory of Molecular Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China. chenhongyan@***. State Key Laboratory of Molecular Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China. liuzh@***. School of Biomedical Engineering School of Ophthalmology & Optometry and Eye Hospital Wenzhou Medical University Wenzhou China. sujz@***. Institute of Biomedical Big Data Wenzhou Medical University Wenzhou China. sujz@***. Oujiang Laboratory Wenzhou China. sujz@***.

来源：评论

学校读者我要写书评

暂无评论

Relational Attention Network for Crowd Counting

Relational Attention Network for Crowd Counting

引用

International Conference on Computer Vision (ICCV)

作者： Anran Zhang Jiayi Shen Zehao Xiao Fan Zhu Xiantong Zhen Xianbin Cao Ling Shao School of Electronic and Information Engineering Beihang University Beijing China Inception Institute of Artificial Intelligence Abu Dhabi UAE Ministry of Industry and Information Technology of China Key Laboratory of Advanced Technology of Near Space Information System (Beihang University) Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beijing China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Crowd counting is receiving rapidly growing research interests due to its potential application value in numerous real-world scenarios. However, due to various challenges such as occlusion, insufficient resolution and dynamic backgrounds, crowd counting remains an unsolved problem in computer vision. Density estimation is a popular strategy for crowd counting, where conventional density estimation methods perform pixel-wise regression without explicitly accounting the interdependence of pixels. As a result, independent pixel-wise predictions can be noisy and inconsistent. In order to address such an issue, we propose a Relational Attention Network (RANet) with a self-attention mechanism for capturing interdependence of pixels. The RANet enhances the self-attention mechanism by accounting both short-range and long-range interdependence of pixels, where we respectively denote these implementations as local self-attention (LSA) and global self-attention (GSA). We further introduce a relation module to fuse LSA and GSA to achieve more informative aggregated feature representations. We conduct extensive experiments on four public datasets, including ShanghaiTech A, ShanghaiTech B, UCF-CC-50 and UCF-QNRF. Experimental results on all datasets suggest RANet consistently reduces estimation errors and surpasses the state-of-the-art approaches by large margins.

关键词： Feature extraction Computational modeling Task analysis Estimation Fuses Correlation Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Weight Learning in Weighted ELM Classification Model Based on Genetic Algorithms

Weight Learning in Weighted ELM Classification Model Based o...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Peng Yao Xi-Zhao Wang Big Data Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen Guangdong China

ISBN: (纸本)9781538652152

In cost sensitive classification problems we often suppose to have a known cost matrix in which each element represents the cost of mistakenly classifying an object from one class into another. Weighted least square, which does not equally consider individual classes and therefore assigns a different weight to each class of samples, is a typical approach to dealing with cost sensitive classification problems. Theoretically and experimentally it is confirmed that reasonable class weights will greatly improve classification ability of a learning model. Unfortunately we only know that these weights depend generally on cost matrix but very few methods can be used to specifically determine these weights according to cost matrix. This paper proposes a weighted least square (WLS) model of random weight network and then successfully uses the model in cost sensitive classification. A genetic algorithm to determine weights of different sample classes based on a cost matrix is given. Model analysis and experimental simulations are conducted. Considering the total misclassification cost as the evaluation index, a comparative study shows that our WLS model is far superior to the existing cost sensitive ELM and cost sensitive naive Bayes models.

关键词： Training Genetic algorithms data models Analytical models Indexes Support vector machines Decision trees

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal knowledge Distillation for Efficient Estimation of Aerial Video Saliency

arXiv

引用

arXiv 2019年

作者： Li, Jia Fu, Kui Zhao, Shengwei Ge, Shiming State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security at University of Chinese Academy of Sciences Beijing100095 China

—The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model. The knowledge of spatial and temporal saliency is first separately transferred from the two complex and redundant teachers to their simple and compact students, and the input scenes are also degraded from high-resolution to low-resolution to remove the probable data redundancy so as to greatly speed up the feature extraction process. After that, the desired spatiotemporal model is further trained by distilling and encoding the spatial and temporal saliency knowledge of two students into a unified network. In this manner, the inter-model redundancy can be further removed for the effective estimation of dynamic saliency on aerial videos. Experimental results show that the proposed approach outperforms ten state-of-the-art models in estimating visual saliency on aerial videos, while its speed reaches up to 28,738 FPS on the GPU platform. Copyright © 2019, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Identification of Cognitive Dysfunction in Patients with T2DM Using Whole Brain Functional Connectivity

引用

Genomics, Proteomics & Bioinformatics 2019年第4期17卷 441-452页

作者： Zhenyu Liu Jiangang Liu Huijuan Yuan Taiyuan Liu Xingwei Cui Zhenchao Tang Yang Du Meiyun Wang Yusong Lin Jie Tian CAS Key Laboratory of Molecular Imaging Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Computer and Information Technology Beijing Jiaotong UniversityBeijing 100044China Department of Endocrinology and Metabolism Henan Provincial People’s Hospital&the People’s Hospital of Zhengzhou UniversityZhengzhou 450003China Department of Radiology Henan Provincial People’s Hospital&the People’s Hospital of Zhengzhou UniversityZhengzhou 450003China Cooperative Innovation Center for Internet Healthcare&School of Software Zhengzhou UniversityZhengzhou 450003China School of Mechanical Electrical&Information EngineeringShandong University(Weihai)Weihai 264209China University of Chinese Academy of Sciences Beijing 100080China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of MedicineBeihang UniversityBeijing 100191China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and TechnologyXidian UniversityXi’an 710126China

Majority of type 2 diabetes mellitus(T2DM)patients are highly susceptible to several forms of cognitive impairments,particularly ***,the underlying neural mechanism of these cognitive impairments remains *** aimed to investigate the correlation between whole brain resting state functional connections(RSFCs)and the cognitive status in 95 patients with *** constructed an elastic net model to estimate the Montreal Cognitive Assessment(MoCA)scores,which served as an index of the cognitive status of the patients,and to select the RSFCs for further ***,we utilized a machine learning technique to evaluate the discriminative ability of the connectivity pattern associated with the selected *** estimated and chronological MoCA scores were significantly correlated with R=0.81 and the mean absolute error(MAE)=***,cognitive impairments of patients with T2DM can be identified using the RSFC pattern with classification accuracy of 90.54%and the area under the receiver operating characteristic(ROC)curve(AUC)of *** connectivity pattern not only included the connections between regions within the default mode network(DMN),but also the functional connectivity between the task-positive networks and the DMN,as well as those within the task-positive *** results suggest that an RSFC pattern could be regarded as a potential biomarker to identify the cognitive status of patients with T2DM.

关键词： Type 2 diabetes mellitus Resting state functional connectivity Elastic net Support vector machines MoCA

来源：评论

学校读者我要写书评

暂无评论

Signal demodulation with machine learning methods for physical layer visible light communications: Prototype platform, open dataset and algorithms

arXiv

引用

arXiv 2019年

作者： Ma, Shuai Dai, Jiahui Lu, Songtao Li, Hang Zhang, Han Du, Chun Li, Shiyin School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China State Key Laboratory of Integrated Services Networks Xidian University Xi'an710071 China Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States Shenzhen Research Institute of Big Data Shenzhen518172 China Department of Electrical and Computer Engineering University of California DavisCA95616 United States

In this paper, we investigate the design and implementation of machine learning (ML) based demodulation methods in the physical layer of visible light communication (VLC) systems. We build a flexible hardware prototype of an end-to-end VLC system, from which the received signals are collected as the real data. The dataset is available online, which contains eight types of modulated signals. Then, we propose three ML demodulators based on convolutional neural network (CNN), deep belief network (DBN), and adaptive boosting (AdaBoost), respectively. Specifically, the CNN based demodulator converts the modulated signals to images and recognizes the signals by the image classification. The proposed DBN based demodulator contains three restricted Boltzmann machines (RBMs) to extract the modulation features. The AdaBoost method includes a strong classifier that is constructed by the weak classifiers with the knearest neighbor (KNN) algorithm. These three demodulators are trained and tested by our online open dataset. Experimental results show that the demodulation accuracy of the three datadriven demodulators drops as the transmission distance increases. A higher modulation order negatively influences the accuracy for a given transmission distance. Among the three ML methods, the AdaBoost modulator achieves the best performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Adaptive boosting

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：