检索结果-内蒙古大学图书馆

International Symposium on Software Reliability engineering (ISSRE)

作者： Minghua He Tong Jia Chiming Duan Huaqian Cai Ying Li Gang Huang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China School of Computer Science Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (数字)9798350353884

ISBN: (纸本)9798350353891

Log-based anomaly detection is an essential task in maintaining software reliability. Existing log-based anomaly detection approaches often consist of three key phases: log parsing, event embedding, and model construction. Event embedding efficiently extracts semantic information from log events and produces vector representations of log events. However, existing event embedding methods suffer from two key problems. First, semantic noises are buried in log events leading to inevitable gaps between the obtained semantics from log events and their essential meanings. Second, there exists a gap between general semantic embedding and the specific embedding requirement of anomaly detection tasks. To mitigate these problems and improve the quality of representations of log events, we propose a novel anomaly detection approach named LLMeLog. It leverages the capabilities of large language models (LLMs) to enrich the contents of log events with in-context learning techniques. Then it utilizes the enriched log events to fine-tune a pre-trained BERT model. At last, it trains a transformer-based anomaly detection model with the event representations produced by the pre-trained BERT model. Evaluation results on three public log datasets show that LLMeLog achieves the best performance across all datasets, boasting F1-scores exceeding 99%. Besides, when using only 10% of labeled data as training data, our approach can still achieve over 90% F1-scores.

关键词： Training Analytical models Large language models Semantics Noise Training data Transformers Vectors Software reliability Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Best Practices for a Handwritten Text Recognition System

arXiv

引用

arXiv 2024年

作者： Retsinas, George Sfikas, Giorgos Gatos, Basilis Nikou, Christophoros School of Electrical and Computer Engineering National Technical University of Athens Greece Computational Intelligence Laboratory Institute of Informatics and Telecommunications National Center for Scientific Research "Demokritos" Greece Department of Computer Science and Engineering University of Ioannina Greece Department of Surveying and Geoinformatics Engineering University of West Attica Greece

Handwritten text recognition has been developed rapidly in the recent years, following the rise of deep learning and its applications. Though deep learning methods provide notable boost in performance concerning text recognition, non-trivial deviation in performance can be detected even when small pre-processing or architectural/optimization elements are changed. This work follows a "best practice" rationale;highlight simple yet effective empirical practices that can further help training and provide well-performing handwritten text recognition systems. Specifically, we considered three basic aspects of a deep HTR system and we proposed simple yet effective solutions: 1) retain the aspect ratio of the images in the preprocessing step, 2) use max-pooling for converting the 3D feature map of CNN output into a sequence of features and 3) assist the training procedure via an additional CTC loss which acts as a shortcut on the max-pooled sequential features. Using these proposed simple modifications, one can attain close to state-of-the-art results, while considering a basic convolutional-recurrent (CNN+LSTM) architecture, for both IAM and RIMES datasets. Code is available at https://***/georgeretsi/HTR-best-practices/. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Constraint Boundary Wandering Framework: Enhancing Constrained Optimization with Deep Neural Networks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wu, Shuang Chen, Shixiang Shen, Li Zhang, Lefei Tao, Dacheng Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China University of Science and Technology of China Key Laboratory of the Ministry of Education for Mathematical Foundations and Applications of Digital Technology School of Mathematical Sciences China Shenzhen Campus of Sun Yat-sen University School of Cyber Science and Technology Shenzhen518107 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

Constrained optimization problems are pervasive in various fields, and while conventional techniques offer solutions, they often struggle with scalability. Leveraging the power of deep neural networks (DNNs) in optimization, we present a novel learning-based approach, the Constraint Boundary Wandering Framework (CBWF), to address these challenges. Our contributions include introducing a boundary wandering strategy inspired by the active-set method, enhancing equality constraint feasibility, and treating the Lipschitz constant as a learnable parameter. Additionally, we evaluate the regularization term, illustrating that the nonsmooth L2 norm yields superior results. Extensive testing on synthetic datasets and the ACOPT dataset demonstrates CBWF's superiority, outperforming existing deep learning-based solvers in terms of both objective and constraint loss. © 1979-2012 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Code interoperability extends the scope of quantum simulations

引用

npj Computational Materials 2021年第1期7卷 302-311页

作者： Marco Govoni Jonathan Whitmer Juan de Pablo Francois Gygi Giulia Galli Materials Science Division and Center for Molecular Engineering Argonne National LaboratoryLemontIL 60439USA Department of Chemical and Biomolecular Engineering University of Notre DameNotre DameIN 46556USA Pritzker School of Molecular Engineering University of ChicagoChicagoIL 60637USA Department of Computer Science University of CaliforniaDavisCA 95616USA Department of Chemistry University of ChicagoChicagoIL 60637USA

The functionality of many materials is critically dependent on the integration of dissimilar components and on the interfaces that arise between *** description of such heterogeneous components requires the development and deployment of first principles methods,coupled to appropriate dynamical descriptions of matter and advanced sampling techniques,in order to capture all the relevant length and time scales of importance to the materials’*** is thus essential to build simple,streamlined computational schemes for the prediction and design of multiple properties of broad classes of materials,by developing interoperable codes which can be efficiently coupled to each other to perform complex *** discuss the use of interoperable codes to simulate the structural and spectroscopic characterization of materials,including chemical reactions for catalysis,the description of defects for quantum information science,and heat and charge transport.

关键词： quantum catalysis spectroscopic

来源：评论

学校读者我要写书评

暂无评论

Neural-Network-Based Recursive State Estimation for Nonlinear Networked Systems With Binary-Encoding Mechanisms

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 10072-10083页

作者： Yuhan Zhang Zidong Wang Lei Zou Wei Qian Shuxin Du College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao China Department of Computer Science Brunel University of London Middlesex Uxbridge U.K. College of Information Science and Technology Donghua University Shanghai China Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of Education Shanghai China School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou China

This work addresses the problem of recursive state estimation for networked control systems with unknown nonlinearities and binary-encoding mechanisms (BEMs). To enhance transmission reliability and reduce network resource consumption, BEMs are used to convert measurement signals into binary bit strings (BBSs) of limited length, which are then transmitted to the estimator through noisy communication channels. During transmission, random bit errors may occur in the BBSs due to channel noise. For the considered nonlinear networked control systems affected by random bit errors, a neural-network (NN)-based recursive estimation strategy is proposed, where an NN with a time-varying tuning scalar is employed to approximate the unknown nonlinearity of the networked control systems. By using the proposed strategy, the upper bounds of the estimation error of the system state and the trace of the estimation error of the NN weight (NNW) are first derived. These bounds are then minimized by recursively designing both the estimator gain matrix and the tuning scalar of the NNW. Finally, the effectiveness of the proposed estimation strategy is demonstrated through a numerical example.

关键词： Artificial neural networks State estimation Encoding Noise Networked control systems Electronic mail Symmetric matrices Estimation error Tuning Recursive estimation

来源：评论

学校读者我要写书评

暂无评论

UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs 25

UICopilot: Automating UI Synthesis via Hierarchical Code Gen...

引用

34th ACM Web Conference, WWW 2025

作者： Gui, Yi Wan, Yao Li, Zhen Zhang, Zhongyi Chen, Dongping Zhang, Hongyu Su, Yi Chen, Bohua Zhou, Xing Jiang, Wenbin Zhang, Xiangliang Huazhong University of Science and Technology Wuhan China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology China

ISBN: (纸本)9798400712746

Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manual effort. Recently, the rapid development of Multimodal Large Language Models (MLLMs) has made it possible to generate front-end Hypertext Markup Language (HTML) code directly from webpage designs. However, real-world webpages encompass not only a diverse array of HTML tags but also complex stylesheets, resulting in significantly lengthy code. The lengthy code poses challenges for the performance and efficiency of MLLMs, especially in capturing the structural information of UI designs. To address these challenges, this paper proposes UICopilot, a novel approach to automating UI synthesis via hierarchical code generation from webpage designs. The core idea of UICopilot is to decompose the generation process into two stages: first, generating the coarse-grained HTML hierarchical structure, followed by the generation of fine-grained code. To validate the effectiveness of UICopilot, we conduct experiments on a real-world dataset, i.e., WebCode2M. Experimental results demonstrate that UICopilot significantly outperforms existing baselines in both automatic evaluation metrics and human evaluations. Specifically, statistical analysis reveals that the majority of human annotators prefer the webpages generated by UICopilot over those produced by GPT-4V. © 2025 Copyright held by the owner/author(s).

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

Distributed online convex optimization with compressed communication 22

Distributed online convex optimization with compressed commu...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Zhipeng Tu Xi Wang Yiguang Hong Lei Wang Deming Yuan Guodong Shi Academy of Mathematics and Systems Science Chinese Academy of Sciences China and Australian Center for Field Robotics School of AMME The University of Sydney Australia Department of Control Science and Engineering Tongji University China College of Control Science and Engineering Zhejiang University China School of Automation Nanjing University of Science and Technology China Australian Center for Field Robotics School of AMME The University of Sydney Australia

ISBN: (纸本)9781713871088

We consider a distributed online convex optimization problem when streaming data are distributed among computing agents over a connected communication network. Since the data are high-dimensional or the network is large-scale, communication load can be a bottleneck for the efficiency of distributed algorithms. To tackle this bottleneck, we apply the state-of-art data compression scheme to the fundamental GD-based distributed online algorithms. Three algorithms with difference-compressed communication are proposed for full information feedback (DC-DOGD), one-point bandit feedback (DC-DOBD), and two-point bandit feedback (DC-DO2BD), respectively. We obtain regret bounds explicitly in terms of time horizon, compression ratio, decision dimension, agent number, and network parameters. Our algorithms are proved to be no-regret and match the same regret bounds, w.r.t. time horizon, with their uncompressed versions for both convex and strongly convex losses. Numerical experiments are given to validate the theoretical findings and illustrate that the proposed algorithms can effectively reduce the total transmitted bits for distributed online training compared with the uncompressed baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Structural Pruning for Vision Models

arXiv

引用

arXiv 2024年

作者： Li, Changhao Li, Haoling Xue, Mengqi Fang, Gongfan Zhou, Sheng Feng, Zunlei Wang, Huiqiong Song, Mingli Song, Jie School of Software Technology Zhejiang University Hangzhou China School of Computer and Computing Science Hangzhou City University Hangzhou China College of Design and Engineering National University of Singapore Singapore Ningbo Innovation Center Zhejiang University Ningbo China College of Computer Science and Technology Zhejiang University Hangzhou China

Structural pruning has emerged as a promising approach for producing more efficient models. Nevertheless, the community suffers from a lack of standardized benchmarks and metrics, leaving the progress in this area not fully comprehended. To fill this gap, we present the first comprehensive benchmark, termed PruningBench, for structural pruning. PruningBench showcases the following three characteristics: 1) PruningBench employs a unified and consistent framework for evaluating the effectiveness of diverse structural pruning techniques;2) PruningBench systematically evaluates 16 existing pruning methods, encompassing a wide array of models (e.g., CNNs and ViTs) and tasks (e.g., classification and detection);3) PruningBench provides easily implementable interfaces to facilitate the implementation of future pruning methods, and enables the subsequent researchers to incorporate their work into our leaderboards. We provide an online pruning platform http://*** for customizing pruning tasks and reproducing all results in this paper. Leaderboard results can be available on https://***/HollyLee2000/PruningBench. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compound Attention and Neighbor Matching Network for Multi-contrast MRI Super-resolution

arXiv

引用

arXiv 2023年

作者： Chen, Wenxuan Wu, Sirui Wang, Shuai Li, Zhongsen Yang, Jia Yao, Huifeng Song, Xiaolei The Center for Biomedical Imaging Research Tsinghua University Beijing100084 China The School of Materials Science and Engineering Tsinghua University Beijing100084 China The Department of Computer Science and Engineering Hongkong University of Science and Technology Hong Kong

Multi-contrast magnetic resonance imaging (MRI) reflects information about human tissue from different perspectives and has many clinical applications. Multi-contrast super-resolution (SR) of MRI could synthesize high-resolution images of one modality from the acquired low-resolution (LR) images, by utilizing the complementary information from another modality. An important prior knowledge of multi-contrast MRI is that, multi-contrast images are obtained with similar or same field-of-views (FOVs). However, existing methods did not exploit this prior;only performing simple concatenation of the reference and LR features, or global feature-matching. Herein, we proposed a novel network architecture with compound-attention and neighbor matching (CANM-Net) for multi-contrast MRI SR. Specifically, to effectively utilize the priors of similar FOVs, CANM-Net proposed a neighborhood-based feature-matching method, which only calculates the similarity of a LR patch with the corresponding patch on the HR reference and its adjacent ones;the compound self-attention with a pyramid-structure effectively captures the dependencies in both spatial and channel dimension. We conduct experiments on the IXI, fastMRI, and in-house datasets, with T2-, T1-weighted images as the LR and reference images, respectively. In 4× and 2× SR tasks, the CANM-Net outperforms state-of-the-art approaches in both retrospective and prospective experiments. The ablation study proves the rationality of CANM-net. Additionally, when the input LR images and the reference HR are imperfectly registered, CANM-Net still achieves the best performance among all test methods. In summary, CANM-Net may have potential in clinical applications, for recovery and enhancement of multi-contrast MRI. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation

arXiv

引用

arXiv 2023年

作者： Shen, Jiachen Wang, Wenxuan Chen, Chen Jiao, Jianbo Liu, Jing Zhang, Yan Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States School of Computer Science University of Birmingham United Kingdom Institute of Automation Chinese Academy of Sciences China

The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs. Thus, it is of increasing importance to fine-tune pre-trained models for medical volumetric segmentation tasks in a both effective and parameter-efficient manner. In this paper, we introduce a new framework named Med-Tuning to realize parameter-efficient tuning (PET) for medical volumetric segmentation task and an efficient plug-and-play module named Med-Adapter for task-specific feature extraction. With a small number of tuned parameters, our framework enhances the 2D baselines’s precision on segmentation tasks, which are pre-trained on natural images. Extensive experiments on three benchmark datasets (CT and MRI modalities) show that our method achieves better results than previous PET methods on volumetric segmentation tasks. Compared to full FT, Med-Tuning reduces the fine-tuned model parameters by up to 4×, with even better segmentation performance. Our project webpage is at https://***/Med-Tuning/. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

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：