检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Haixia Li, Boxiao Yang, Can Wang, Yang School of Mathematics and Statistics Institute of Interdisciplinary Research for Mathematics and Applied Science Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Hubei Wuhan China School of Mathematics and Statistics Huazhong University of Science and Technology Hubei Wuhan China Department of Mathematics The Hong Kong University of Science and Technology Clear Water Bay China

Numerous studies have shown that label noise can lead to poor generalization performance, negatively affecting classification accuracy. Therefore, understanding the effectiveness of classifiers trained using deep neural networks in the presence of noisy labels is of considerable practical significance. In this paper, we focus on the error bounds of excess risks for classification problems with noisy labels within deep learning frameworks. We begin by exploring loss functions with noise-tolerant properties, ensuring that the empirical minimizer on noisy data aligns with that on the true data. Next, we estimate the error bounds of the excess risks, expressed as a sum of statistical error and approximation error. We estimate the statistical error on a dependent (mixing) sequence, bounding it with the help of the associated independent block sequence. For the approximation error, we first express the classifiers as the composition of the softmax function and a continuous function from [0, 1]d to RK. The main task is then to estimate the approximation error for the continuous function from [0, 1]d to RK. Finally, we focus on the curse of dimensionality based on the low-dimensional manifold assumption. Copyright © 2025, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Lie Point Symmetries of Differential-Difference Equations

引用

Communications in Theoretical Physics 2004年第5期41卷 645-648页

作者： DING Wei~1 TANG Xiao-Yan~(2,3) 1 Department of Applied Mathematics,Shanghai Jiao Tong University,Shanghai 200030,China2 Department of Physics,Shanghai Jiao Tong University,Shanghai 200030,China3 state key laboratory of scientific and engineering computing,Institute of Computational Mathematics and scientific engineering computing,Academy of Mathematics and System Sciences,the Chinese Academy of Sciences,P.O.Box 2719,Beijing 100080,China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific Engineering Computing Academy of Mathematics and System Sciences the Chinese Academy of Sciences P.O. Box 2719 Beijing 100080 China

In this paper,the classical Lie group approach is extended to find some Lie point symmetries of differential-difference *** reveals that the obtained Lie point symmetries can constitute a Kac-Moody-Virasoro algebra.

关键词： Lie point symmetry differential-difference equation Kac Moody-Virasoro algebra

来源：评论

学校读者我要写书评

暂无评论

Cluster Assumption-Guided Timestamp-Supervised Temporal Action Segmentation

引用

IEEE Transactions on Multimedia 2025年

作者： Ren, Ziyou Li, Guozhang Cheng, Nan Wu, Anqi Wang, Nannan Gao, Xinbo Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China Carnegie Mellon University Robotics Institute School of Computer Science PittsburghPA15213 United States Beijing Normal University School of Artificial Intelligence Haidian District Beijing100875 China Georgia Institute of Technology School of Computational Science and Engineering College of Computing AtlantaGA30308 United States Xidian University School of Electronic Engineering Xi'an710071 China Chongqing University of Posts and Telecommunications Chongqing Key Laboratory of Image Cognition Chongqing400065 China

Current timestamp-supervised temporal action segmentation (TS-TAS) methods typically follow a two-phase pipeline: initializing the model with timestamp labels and refining it with pseudo-labels. However, limited by the sparsity of timestamp annotations, current methods' performance is sub-optimal. Specifically, initializing the model with only timestamp annotations may cause overfitting to labeled frames. Additionally, sparse timestamp annotations cannot capture the diverse action representations throughout the whole instance, especially those near the ambiguous action boundaries, leading to pseudo-label noise. Inspired by the cluster assumption of semi-supervised learning (SSL) that points within the same manifold likely share the same label, we here model TS-TAS as an SSL problem. Specifically, we propose a Temporal Embedding Consistency (TEC) strategy to mitigate the excessive focus on annotated frames. The TEC strategy encourages frames with similar representations within the video to have similar classification probability distributions, thereby propagating labeled frames' information to implicit ones. Besides, we design a TS-Mix strategy to further leverage unlabeled data to mitigate the influence of pseudo-label noise in a consistency regularization manner. The TS-Mix strategy includes intra-mix, which adds linear interpolation of two adjacent timestamps to every frame between them, and inter-mix, which mixes frames from two different untrimmed videos frame-by-frame. Then the mixed video is trained with the correspondingly mixed pseudo-labels. Comprehensive experimental results on different benchmarks show that we achieve new state-of-the-art performances. Furthermore, the proposed method can seamlessly enhance existing methods, significantly improving their performances. © 1999-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Order conditions of two kinds of canonical difference schemes

引用

Computers and Mathematics with Applications 1993年第6期25卷 61-74页

作者： Wen-Jie Zhu Meng-Zhao Qin State Key Laboratory of Scientific Engineering Computing Computing Center Academia Sinica Beijing 100080 China

The main purpose of this paper is to develop and simplify the general conditions for an s-stage explicit canonical difference scheme to be of qth order while the simplified order conditions for canonical RKN methods, ...

The main purpose of this paper is to develop and simplify the general conditions for an s-stage explicit canonical difference scheme to be of q^th order while the simplified order conditions for canonical RKN methods, which are applied to special kinds of second order ordinary differential equations, are also obtained here. © 1993.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KANsformer for Scalable Beamforming

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Xie, Xinke Lu, Yang Chi, Chong-Yung Chen, Wei Ai, Bo Niyato, Dusit Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation Beijing100044 China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China National Tsing Hua University Institute of Communications Engineering Department of Electrical Engineering Hsinchu30013 Taiwan Beijing Jiaotong University School of Electronics and Information Engineering Beijing100044 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

This paper proposes an unsupervised deep-learning (DL) approach by integrating Transformer and Kolmogorov-Arnold networks (KAN) termed KANsformer to realize scalable beamforming for mobile communication systems. Specifically, we consider a classic multi-input single-output energy efficiency maximization problem subject to the total power budget. The proposed KANsformer first extracts hidden features via a multi-head self-attention mechanism and then reads out the desired beamforming design via KAN. Numerical results are provided to evaluate the KANsformer in terms of generalization performance, transfer learning and ablation experiment. Overall, the KANsformer outperforms the existing benchmark DL approaches, and is adaptable to the variation in the number of mobile users with real-time and near-optimal inference. © 1967-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Deep Graph Reinforcement Learning for UAV-Enabled Multi-User Secure Communications

引用

IEEE Transactions on Mobile computing 2025年

作者： Tang, Xiao Zhao, Kexin Shen, Chao Du, Qinghe Wang, Yichen Niyato, Dusit Han, Zhu Research & Development Institute Northwestern Polytechnical University Shenzhen518063 China National Key Laboratory of Wireless Communications Chengdu611731 China State Key Laboratory of Intelligent Game Taicang215400 China Northwestern Polytechinical University School of Electronics and Information Xi'an710072 China Xi'an Jiaotong University Faculty of Electronics and Information Engineering Xi'an710049 China Nanyang Technological University College of Computing and Data Science Singapore University of Houston Department of Electrical and Computer Engineering Houston77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

While unmanned aerial vehicles (UAVs) with flexible mobility are envisioned to enhance physical layer security in wireless communications, the efficient security design that adapts to such high network dynamics is rather challenging. The conventional approaches extended from optimization perspectives are usually quite involved, especially when jointly considering factors in different scales such as deployment and transmission in UAV-related scenarios. In this paper, we address the UAV-enabled multi-user secure communications by proposing a deep graph reinforcement learning framework. Specifically, we reinterpret the security beamforming as a graph neural network (GNN) learning task, where mutual interference among users is managed through the message-passing mechanism. Then, the UAV deployment is obtained through soft actor-critic reinforcement learning, where the GNN-based security beamforming is exploited to guide the deployment strategy update. Simulation results demonstrate that the proposed approach achieves near-optimal security performance and significantly enhances the efficiency of strategy determination. Moreover, the deep graph reinforcement learning framework offers a scalable solution, adaptable to various network scenarios and configurations, establishing a robust basis for information security in UAV-enabled communications. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical-control-based output synchronization of coexisting attractor networks

引用

Chinese Physics B 2010年第2期19卷 127-134页

作者：宋运忠唐贻发 Complex Networks Laboratory College of Electrical Engineering&AutomationHenan Polytechnic University State Key Laboratory of Scientific&Engineering Computing Academy of Mathematics&Systems ScienceChinese Academy of Sciences

This paper introduces the concept of hierarchical-control-based output synchronization of coexisting attractor networks. Within the new framework, each dynamic node is made passive at first utilizing intra-control around its own arena. Then each dynamic node is viewed as one agent, and on account of that, the solution of output synchronization of coexisting attractor networks is transformed into a multi-agent consensus problem, which is made possible by virtue of local interaction between individual neighbours; this distributed working way of coordination is coined as inter-control, which is only specified by the topological structure of the network. Provided that the network is connected and balanced, the output synchronization would come true naturally via synergy between intra and inter-control actions, where the rightness is proved theoretically via convex composite Lyapunov functions. For completeness, several illustrative examples are presented to further elucidate the novelty and efficacy of the proposed scheme.

关键词： hierarchical control passive control composite Lyapunov function the Newton--Leipnik equation attractor

来源：评论

学校读者我要写书评

暂无评论

Ultra Broadband Emission Toward White Leds Based on Dysprosium Double Perovskites Csxrb3-Xdycl6-Xix

SSRN

引用

SSRN 2025年

作者： Bai, Xue Jin, Zongqing Xiao, Guanjun Zou, Bo Ge, Qingqin Shi, Nannan Jiang, Liwei Sun, Cheng Xiong, Tao Zhang, Yinan College of Physical Science and Technology Dalian University Dalian116622 China Liaoning Engineering Laboratory of Optoelectronic Information Technology Dalian116622 China State Key Laboratory of Superhard Materials College of Physics Jilin University Changchun130012 China Thermo Fisher Scientific China Shanghai201203 China College of Physics Jilin University Changchun130012 China

Lead-free halide double perovskite (HDP) materials have become one of the hot spots due to their remarkable photoelectric properties, including broadband emission characteristics of self-trapped excitons from soft lattice and strong exciton-phonon coupling. However, the optical and optoelectronic properties are hampered in the visible and infrared region, because of a wide or indirect band gap in metal HDPs. So far, doping lanthanide ions is an efficient method to modify the optical properties of HDP materials. Here, we have successfully synthesized dysprosium-based double perovskite (CsxRb3-xDyCl6-xIx) crystals through a straightforward hydrothermal method. A very broad emission band covering almost the whole visible spectrum from 400 nm to 700 nm is fulfilled, resulting in a strong white light emission. Further, the hue of the white light can finely be adjusted, via tuning the excitation wavelength, high pressure-induced luminescence enhancement has also been demonstrated. Based on the CsxRb3-xDyCl6-xIx crystals, we have also fabricated a series of white light-emitting diodes, with the color coordinates of (0.33, 0.33), illustrating its great potential in the solid-state lighting applications. The dysprosium-based double perovskite studied in this work offers us a nice choice for designing HDP-based white light emitting devices. © 2025, The Authors. All rights reserved.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Unified Anomaly Segmentation

Towards Accurate Unified Anomaly Segmentation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Wenxin Ma Qingsong Yao Xiang Zhang Zhelong Huang Zihang Jiang S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) USTC Suzhou Institute for Advance Research Suzhou Jiangsu China Stanford University Palo Alto California United State School of Medicine Shanghai University Shanghai China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations to distinguish and precisely localize anomalies. Despite recent advancements in the efficient and unified one-for-all scheme, challenges persist in accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by the widely-used AUROC metric under imbalanced UAD settings. This motivates us to emphasize the significance of precise segmentation of anomaly pixels using pAP and DSC as metrics. To address the unsolved segmentation task, we introduce the Unified Anomaly Segmentation (UniAS). UniAS presents a multi-level hybrid pipeline that progressively enhances normal information from coarse to fine, incorporating a novel multi-granularity gated CNN (MGG-CNN) into Transformer layers to explicitly aggregate local details from different granularities. UniAS achieves state-of-the-art anomaly segmentation performance, attaining 65.12/59.33 and 40.06/32.50 in pAP/DSC on the MVTec-AD and VisA datasets, respectively, surpassing previous methods significantly. The codes are shared at https://***/Mwxinnn/UniAS.

关键词： Measurement Image segmentation Computer vision Codes Pipelines Logic gates Transformers Data models Monitoring Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models

arXiv

引用

arXiv 2025年

作者： Zhang, Quanjun Fang, Chunrong Zheng, Yi Zhang, Yaxin Zhao, Yuan Huang, Rubing Zhou, Jianyi Yang, Yun Zheng, Tao Chen, Zhenyu Department of Computing Technologies Swinburne University of Technology Melbourne Australia State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China School of Computer Science and Engineering Macau University of Science and Technology Jiangsu Nanjing China Huawei Cloud Computing Technologies Co. Ltd. Beijing China Shenzhen Research Institute of Nanjing University Guangdong Shenzhen China

Unit testing validates the correctness of the units of the software system under test and serves as the cornerstone in improving software quality and reliability. To reduce manual efforts in writing unit tests, some techniques have been proposed to generate test assertions automatically, including deep learning (DL)-based, retrieval-based, and integration-based ones. Among them, recent integration-based approaches inherit from both DL-based and retrieval-based approaches and are considered state-of-the-art. Despite being promising, such integration-based approaches suffer from inherent limitations, such as retrieving assertions with lexical matching while ignoring meaningful code semantics, and generating assertions with a limited training corpus. In this paper, we propose a novel Retrieval-Augmented Deep Assertion Generation approach, namely RetriGen, based on a hybrid assertion retriever and a pre-trained language model (PLM)-based assertion generator. Given a focal-test, RetriGen first builds a hybrid assertion retriever to search for the most relevant test-assert pair from external codebases. The retrieval process takes both lexical similarity and semantical similarity into account via a token-based and an embedding-based retriever, respectively. RetriGen then treats assertion generation as a sequence-to-sequence task and designs a PLM-based assertion generator to predict a correct assertion with historical test-assert pairs and the retrieved external assertion. Although our concept is general and can be adapted to various off-the-shelf encoder-decoder PLMs, we implement RetriGen to facilitate assertion generation based on the recent CodeT5 model. We conduct extensive experiments to evaluate RetriGen against six state-of-the-art approaches across two large-scale datasets and two metrics. The experimental results demonstrate that RetriGen achieves 57.66% and 73.24% in terms of accuracy and CodeBLEU, outperforming all baselines with an average improvement of 50.66

关键词： Semantics

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：