检索结果-内蒙古大学图书馆

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Xinlong Li Da Huang Wenjing Yang Xueqiong Li Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China

ISBN: (纸本)9781665412971

Radio modulation recognition is the key link of modern electronic warfare. This paper applies the idea of deep learning to radio modulation recognition. Since the modulation type is the most important information about the subtle features of the radio signal, we use short time Fourier transform (STFT) to convert the radio signal into a time-frequency distribution map to form a joint distribution of frequency and time. The attention-based convolutional neural network is used to classify and recognize the modulation types of time-frequency distribution maps. The simulation results show that time-frequency analysis can improve the accuracy of recognition, and adding attention can effectively improve the performance of the network.

关键词： Training Seminars Time-frequency analysis Electronic warfare Fourier transforms Simulation Noise reduction

来源：评论

学校读者我要写书评

暂无评论

Implicit Feature Alignment For Knowledge Distillation

Implicit Feature Alignment For Knowledge Distillation

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Dingyao Chen Mengzhu Wang Xiang Zhang Tianyi Liang Zhigang Luo College of computer National University of Defense Technology Changshan Hunan P.R. China Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha Hunan P.R. China

Knowledge distillation is a technique of transferring knowledge from a large teacher network to a light student one. Existing studies purely use immediate layers' features for distillation and may fail to gain insufficient semantic knowledge from the teacher. Inspired by recent advances in contrastive learning, we propose to introduce extra light embedding layers of the teacher to enforce its generalization ability and further align the mixup-type features for knowledge distillation in an implicit fashion (IFKD). IFKD allows the student to learn richer structural knowledge, thanks to the learned embedding layers of the teacher. Crucially, benefitting from a plethora of mixed samples, we can further adequately mine much semantic knowledge of the teacher. For efficiency, we propose a simple reversed mixup scheme to organize images and implicitly ensure complete positive information comparisons. Extensive experiments on image classification on two popular datasets including CIFAR-100 and ImageNet verify the effectiveness of our approach as compared to the previous methods.

关键词： Knowledge engineering Semantics Image classification

来源：评论

学校读者我要写书评

暂无评论

ISort: SSD Internal Sorting Algorithm for Big Data

引用

Mobile Information Systems 2022年第1期2022卷

作者： Liu, Yang Chen, Wenhan Ge, Xuran Chen, Zhiguang Ou, Yang Xiao, Nong Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Hunan Province Changsha City410000 China Sun Yat-sen University Guangzhou Province Guangzhou City510000 China Institute of Computing Technology College of Computer National University of Defense Technology Hunan Province Changsha City410000 China

As a basic algorithm for big data processing, external sorting suffers from massive read and write operations in the external memory. Recent works separate part of the data processing work from the host side to the solid state drive (SSD) to reduce data transmission. However, the internal memory of the SSD is limited, and undesirable data retention could occur during the merge phase. Therefore, to improve the efficiency of memory, we propose an algorithm named ISort. Specifically, we build an index table between the memory and the address. The index table determines the order of pages being read in the merge phase according to their minimum values, which are read into memory sequentially to reduce the data residing in memory and improve memory efficiency. Since the merge phase is performed inside the SSD, ISort can take advantage of the high IO bandwidth within the SSD to speed up the execution of the merge phase. We search for the optimal ratio of read and write channels by comparing the "specialized channel"and the "hybrid channel"for data of read and write performance because the utilization of the channel will directly influence performance. Experimental results show that ISort can maintain better data processing speed when SSD memory is limited, outperforming other robust algorithms. In addition, the algorithm's performance using the crossover strategy is better than that using the specialization strategy. © 2022 Yang Liu et al.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Area-efficient memristor spiking neural networks and supervised learning method

引用

Science China(Information Sciences) 2019年第9期62卷 196-198页

作者： Errui ZHOU Liang FANG Rulin LIU Zhensen TANG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology

Dear editor,Memristors have attracted a lot of attention since HP Labs first reported their memristive devices [1].They have been employed in many fields, including non-volatile memory, image processing, and neuromorphic computing [2–4]. In neuromorphic computing, memristors are usually used as synapses because they can store synaptic weights by their conductance [4]. Most memristors have the struc-

关键词： simulation Area-efficient memristor spiking neural networks and supervised learning method

来源：评论

学校读者我要写书评

暂无评论

UCTB: An Urban computing Tool Box for Building Spatiotemporal Prediction Services

UCTB: An Urban Computing Tool Box for Building Spatiotempora...

引用

Software Services Engineering (SSE) IEEE International Conference on

作者： Jiangyi Fang Liyue Chen Di Chai Yayao Hong Xiuhuai Xie Longbiao Chen Leye Wang Key Lab of High Confidence Software Technologies Ministry of Education China School of Computer Science Peking University Beijing Hong Kong University of Science and Technology Hong Kong Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen School of Informatics Xiamen University Xiamen

ISBN: (数字)9798350368512

ISBN: (纸本)9798350368529

Spatiotemporal prediction (STP) service is one of the key infrastructure applications in smart cities. Currently, most of the existing STP services are constructed following the workflow of building deep learning (DL) applications while neglecting the importance of domain knowledge and region partition. However, the performance and interpretability of STP are highly related to them. As a result, there is an urgent requirement to develop a thorough and tailored workflow for STP services. To address this gap, we propose a novel workflow including two factors above as intermediate procedures. Based on the workflow, we design and implement an STP toolbox called UCTB (Urban computing Tool Box) assisting practitioners in the rapid construction of STP services, which can manage multiple spatiotemporal do-main knowledge, support various region partition algorithms, and possess state-of-the-art models simultaneously. The relevant code and supporting documents have been open-sourced at https://***/uctb/UCIB.

关键词： Deep learning Smart cities Buildings Predictive models Prediction algorithms Software Extensibility

来源：评论

学校读者我要写书评

暂无评论

Enhancing Oxygen Reduction Reaction in PdHx@Pt Metallenes: Unveiling the Impact of Ligand Beyond Strain Effect

引用

Advanced Functional Materials 2025年

作者： Feng, Zhipeng Jiao, Dongxu Fan, Jinchang Qiu, Yu Ge, Xin Wang, Jiaqi Zhao, Xiao Zhang, Wei Zheng, Lirong Zhang, Lei Yu, Zhigen Zheng, Weitao Cui, Xiaoqiang School of Materials Science and Engineering Key Laboratory of Automobile Materials Electron Microscopy Center Jilin University No.2699 Qianjin Street Changchun130012 China Beijing Synchrotron Radiation Facility Institute of High Energy Physics Chinese Academy of Sciences No.19 Yuquan Road Beijing100049 China College of Chemistry Jilin University No.2699 Qianjin Street Changchun130012 China Institute of High-Performance Computing Agency for Science Technology and Research No.1 Fusionopolis Way Singapore138632 Singapore

Incorporating interstitial non-metal atoms within the crystal lattice of catalysts enables flexible modulation of their electronic structures and catalytic performances. However, the resulting induced tensile strain typically has a detrimental effect on oxygen reduction reaction (ORR) activity. In this study, a series of PdHx@Pt metallenes with varying H/Pd ratios, where hydrogen atoms precisely modulate the strain and ligand effects on the Pt skin surface is reported. Notably, PdH0.35@Pt metallenes exhibit an extraordinary half-wave potential of 0.933 V and a mass activity (MA) of 7.36 A mgPt−1 at 0.9 V vs reversible hydrogen electrode (RHE) for ORR, outperforming both Pd@Pt metallenes and commercial Pt/C catalysts. Control experiments and density functional theory (DFT) calculations reveal a competitive relationship between strain and ligand effects across different H/Pd ratios, with a dominant positive ligand effect overcoming the negative strain effect at an H/Pd ratio of 0.35. This electronic structure modulation leads to an increased 5d electron density of the surface Pt and a downshift in the eg* band center, thereby weakening the adsorption of oxygen intermediates on the Pt skin surface and resulting in excellent ORR activity. © 2025 Wiley-VCH GmbH.

关键词： Ligands

来源：评论

学校读者我要写书评

暂无评论

Decoupled adaptive convolutional neural networks for the few-shot image classification 4

Decoupled adaptive convolutional neural networks for the few...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2021

作者： Huang, Wanrong Hu, Yaqing Hu, Shuofeng Liu, Jingde Artificial Intelligence Research Center National Innovation Institute of Defense Technology Beijing China National University of Defense Technology State Key Laboratory of High Performance Computing Changsha China Center for Computational Biology Beijing Institute of Basic Medical Sciences Beijing China College of Joint Operation National Defense University Beijing China

ISBN: (纸本)9781665413220

Deep neural networks have achieved remarkable results in large-scale data domain. However, few-shot image classification is still a difficult and important problem. In this work, we analyze recently proposed deep neural networks of the meta-learning ability enable them to solve few-shot tasks, and try to find out where the ability comes from. Based on the analysis, we conclude a unified meta-learning framework for the few-shot tasks and propose a novel meta-learning network composed of two decoupled convolutional channels. One of them uses a typical convolutional neural network (CNN) to classify the query sample. The other channel is responsible for adaptively generating the parameters of the CNN with the support images. Unlike previous work in which the query and support input always share modules, our approach improves the flexibility and adaptability via decoupling the two channels. We demonstrate that our approach is able to achieve competitive performance with the existing state-of-the-art methods on two common few-shot image classification benchmarks while being substantially simpler and easier to train on. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Learning A Linear Classifier by Transforming Feature Vectors for Few-shot Image Classification 21

Learning A Linear Classifier by Transforming Feature Vectors...

引用

2nd International Conference on Control, Robotics and Intelligent System, CCRIS 2021

作者： Huang, Wanrong Hu, Yaqing Hu, Shuofeng Liu, Jingde Artificial Intelligence Research Center National Innovation Institute of Defense Technology Beijing China State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China Center for Computational Biology Beijing Institute of Basic Medical Sciences Beijing China College of Joint Operation National Defense University Beijing China

ISBN: (纸本)9781450390453

Deep neural networks have achieved remarkable results in large-scale data domain. However, they have not performed well on few-shot image classification tasks. Here we propose a new meta-learning approach composed of an embedding network and a linear classifier learner. During the training phase, our approach (called Transformation Network) learns to learn a classifier by transforming the feature vectors produced by the embedding module. Once trained, a Transformation Network is able to classify images of new classes by the learned classifier. The ability of learning a discriminatively trained classifier could make our architecture adapt fast to new examples from unseen classes. We further describe implementation details upon the architecture convolutional networks and linear transformation operations. We demonstrate that our approach achieves improved performance on few-shot image classification tasks on two benchmarks and a self-made dataset. © 2021 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

dugMatting: Decomposed-Uncertainty-Guided Matting

arXiv

引用

arXiv 2023年

作者： Wu, Jiawei Zhang, Changqing Li, Zuoyong Fu, Huazhu Peng, Xi Zhou, Joey Tianyi College of Mechanical and Electrical Engineering Fujian Agriculture and Forestry University Fuzhou China College of Intelligence and Computing Tianjin University Tianjin China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China Institute of High Performance Computing Agency for Science Technology and Research Singapore College of Computer Science Sichuan University Chengdu China Singapore

Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typically user-defined trimaps or scribbles, are usually needed to reduce the uncertainty. Although effective, it is either time consuming or only suitable for experienced users who know where to place the strokes. In this work, we propose a decomposed-uncertainty-guided matting (dugMatting) algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results. Basing on the characteristic of these uncertainties, the epistemic uncertainty is reduced in the process of guiding interaction (which introduces prior knowledge), while the aleatoric uncertainty is reduced in modeling data distribution (which introduces statistics for both data and possible noise). The proposed matting framework relieves the requirement for users to determine the interaction areas by using simple and efficient labeling. Extensively quantitative and qualitative results validate that the proposed method significantly improves the original matting algorithms in terms of both efficiency and efficacy. Copyright © 2023, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Reduced Basis Method Based on a Posteriori Error Estimate for the Parameterized Allen-Cahn Equation

SSRN

引用

SSRN 2024年

作者： Wu, Liang Azaïez, Mejdi Chacón Rebollo, Tomás Xu, Chuanju School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen University Xiamen361005 China Université de Bordeaux I2M UMR CNRS 5295 Pessac33607 France Departamento EDAN & IMUS Universidad de Sevilla Spain

In this paper we propose an efficient and accurate reduced-order method for the parameterized Allen-Cahn equation. The proposed method aims to construct efficient low-dimensional reduced basis to approximate the Allen-Cahn equation with desired accuracy for all parameters of interest. The key is to select a few optimal parameters for which the snapshots are collected to generate the reduced basis. The selection of these optimal parameters is guided by a residual estimator. To this end, we first derive a posteriori error estimates for this residual estimator. Then, we propose a PODgreedy algorithm based on the derived a posteriori error estimates to construct the efficient reduced basis. The established a posteriori error estimate and the accuracy of the proposed reduced-order method are verified through several numerical examples. In particular, the efficiency of the POD-greedy sampling procedure is demonstrated by some practical examples. © 2024, The Authors. All rights reserved.

关键词： Numerical methods

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：