检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yi, Liping Yu, Han Ren, Chao Wang, Gang Liu, Xiaoguang Li, Xiaoxiao College of Computer Science TMCC SysNet DISSec GTIISC Nankai University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

Model heterogeneous federated learning (MHeteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion. However, existing MHeteroFL methods rely on training loss to transfer knowledge between the client model and the server model, resulting in limited knowledge exchange. To address this limitation, we propose the Federated model heterogeneous Matryoshka Representation Learning (FedMRL) approach for supervised learning tasks. It adds an auxiliary small homogeneous model shared by clients with heterogeneous local models. (1) The generalized and personalized representations extracted by the two models' feature extractors are fused by a personalized lightweight representation projector. This step enables representation fusion to adapt to local data distribution. (2) The fused representation is then used to construct Matryoshka representations with multi-dimensional and multi-granular embedded representations learned by the global homogeneous model header and the local heterogeneous model header. This step facilitates multi-perspective representation learning and improves model learning capability. Theoretical analysis shows that FedMRL achieves a O(1/T) non-convex convergence rate. Extensive experiments on benchmark datasets demonstrate its superior model accuracy with low communication and computational costs compared to seven state-of-the-art baselines. It achieves up to 8.48% and 24.94% accuracy improvement compared with the state-of-the-art and the best same-category baseline, respectively. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of GPT-4 in Automated Mentoring for Programming Courses 2023

Exploring the Potential of GPT-4 in Automated Mentoring for ...

引用

2nd ACM Conference on Global computing Education, CompEd 2023

作者： Balse, Rishabh Prasad, Prajish Warriem, Jayakrishnan Madathil Bs Programme in Data Science and Applications Indian Institute of Technology Madras Tamil Nadu Chennai India School of Computing and Data Sciences Flame University Maharashtra Pune India Indian Institute of Technology Madras Tamil Nadu Chennai India

ISBN: (纸本)9798400703744

This research proposes an AI-assisted mentoring system for programming education, leveraging the advanced capabilities of OpenAI's GPT-4. We aim to validate students' pseudocode or algorithmic approaches to Python programming problems within the context of a Tier-1 institution in India, where the high student-to-mentor ratio presents unique challenges. The proposed system aspires to alleviate the pressures of the current mentoring system, providing a more accessible, responsive, and effective educational support system. © 2023 Owner/Author.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network Art Generator for Sculpture Analysis

Generative Adversarial Network Art Generator for Sculpture A...

引用

International Conference on Communication, computing and Internet of Things (IC3IoT)

作者： Swagat Subhash Kalita Parag Mahajan S. Sharanya Data Science and Business System School of Computing SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350352689

ISBN: (纸本)9798350352696

This study examines computer-generated sculpture using a hybrid architecture of Generative Adversarial Networks (GANs) and Convolutional Neural Networks (CNNs). CNNs are essential for visual data analysis and processing, while GANs iteratively blur the line between synthesis and authenticity. A dynamically interacting generator and discriminator network form the GAN framework. The discriminator, trained to distinguish authentic sculptures from computer-generated ones, guides the generator toward greater realism and complexity with each iteration. This study analyzes the complicated dynamics of GAN-enabled sculpture production, examining several elements that affect the result. We intend to illuminate the complex relationship between composition, texture, and shape of digitally generated sculptures by analyzing sculptures using GANs and CNNs. We want to understand their formation methods as well as their aesthetic value. We also consider how GAN-generated sculptures may be transformed beyond traditional artistic usage. The sculptures offer unique opportunities for artistic expression, scholarly study, and practical use. They can enhance art, education, architectural design, and historical preservation. This thorough inquiry using GANs and CNNs aims to push the limitations of traditional art creation and explore unknown sculpture interpretation and analysis zones.

关键词： Training Visualization Art Shape Neural networks Production Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators 31

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Impact of Population Shift Across Age and Sex for Abdominal Organ Segmentation 2nd

Quantifying the Impact of Population Shift Across Age and...

引用

2nd International Workshop on Fairness of AI in Medical Imaging, FAIMI 2024, and 3rd International Workshop on Ethical and Philosophical Issues in Medical Imaging, EPIMI 2024, Held in Conjunction with the International Conference on Medical Image computing and Computer Assisted Interventions, MICCAI 2024

作者： Čevora, Kate Glocker, Ben Bai, Wenjia Department of Computing Imperial College London London United Kingdom Department of Brain Sciences Imperial College London London United Kingdom Data Science Institute Imperial College London London United Kingdom

ISBN: (纸本)9783031727863

Deep learning-based medical image segmentation has seen tremendous progress over the last decade, but there is still relatively little transfer into clinical practice. One of the main barriers is the challenge of domain generalisation, which requires segmentation models to maintain high performance across a wide distribution of image data. This challenge is amplified by the many factors that contribute to the diverse appearance of medical images, such as acquisition conditions and patient characteristics. The impact of shifting patient characteristics such as age and sex on segmentation performance remains relatively under-studied, especially for abdominal organs, despite that this is crucial for ensuring the fairness of the segmentation model. We perform the first study to determine the impact of population shift with respect to age and sex on abdominal CT image segmentation, by leveraging two large public datasets, and introduce a novel metric to quantify the impact. We find that population shift is a challenge similar in magnitude to cross-dataset shift for abdominal organ segmentation, and that the effect is asymmetric and dataset-dependent. We conclude that dataset diversity in terms of known patient characteristics is not necessarily equivalent to dataset diversity in terms of image features. This implies that simple population matching to ensure good generalisation and fairness may be insufficient, and we recommend that fairness research should be directed towards better understanding and quantifying medical image dataset diversity in terms of performance-relevant characteristics such as organ morphology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Thematic Event Extraction Based on Event-Related Sentence Detection 1

Thematic Event Extraction Based on Event-Related Sentence De...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Zhang, Xing Guo, Yucan Jin, Xiaolong Liang, Haozhe Guan, Saiping School of Computer Science and Technology University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences Cas Key Laboratory of Network Data Science and Technology China Institute of Systems Engineering Academy of Military Science Australia

ISBN: (纸本)9798350358780

Existing works in event extraction typically extract event arguments within the sentence scope. However, besides the sentence level, events may also be naturally presented at the document level. A document-level event usually reflects, to some extent, the theme (i.e., the main content) of the document (e.g., electronic medical records and news articles), which is thus referred to as the thematic event. Thematic Event Extraction (TEE) aims to extract the arguments of thematic events. TEE faces a major challenge, i.e., the sparsity and dispersion of arguments, which means that the arguments of a thematic event are dispersed in different sentences of the document. To overcome this challenge, we propose an Event-related Sentence Detection based TEE model, called ESDTEE, which first detects the sentences related to the thematic event and then extracts the arguments only within these detected sentences using existing models. Extensive experiments with comprehensive analyses demonstrate the effectiveness of ESDTEE. © 2023 IEEE.

关键词： Medical computing

来源：评论

学校读者我要写书评

暂无评论

An Adjusted Gray Map Technique for Constructing Large Four-Level Uniform Designs

引用

Journal of Systems science & Complexity 2023年第1期36卷 433-456页

作者： ELSAWAH A M VISHWAKARMA G K MOHAMED H S FANG Kai-Tai Department of Statistics and Data Science Faculty of Science and TechnologyBeijing Normal University-Hong Kong Baptist University United International CollegeZhuhai 519087China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International CollegeZhuhai 519087China Department of Mathematics Faculty of ScienceZagazig UniversityZagazig 44519Egypt Department of Mathematics&Computing Indian Institute of Technology DhanbadDhanbad 826004India College of Transportation and Civil Engineering Fujian Agriculture and Forestry UniversityFuzhou 350002China The Key Lab of Random Complex Structures and Data Analysis The Chinese Academy of SciencesBeijing 100190China

A uniform experimental design(UED)is an extremely used powerful and efficient methodology for designing experiments with high-dimensional inputs,limited resources and unknown underlying models.A UED enjoys the following two significant advantages:(i)It is a robust design,since it does not require to specify a model before experimenters conduct their experiments;and(ii)it provides uniformly scatter design points in the experimental domain,thus it gives a good representation of this domain with fewer experimental trials(runs).Many real-life experiments involve hundreds or thousands of active factors and thus large UEDs are *** large UEDs using the existing techniques is an NP-hard problem,an extremely time-consuming heuristic search process and a satisfactory result is not *** paper presents a new effective and easy technique,adjusted Gray map technique(AGMT),for constructing(nearly)UEDs with large numbers of four-level factors and runs by converting designs with s two-level factors and n runs to(nearly)UEDs with 2^(t−1)s four-level factors and 2tn runs for any t≥0 using two simple transformation *** justifications for the uniformity of the resulting four-level designs are given,which provide some necessary and/or sufficient conditions for obtaining(nearly)uniform four-level *** results show that the AGMT is much easier and better than the existing widely used techniques and it can be effectively used to simply generate new recommended large(nearly)UEDs with four-level factors.

关键词： Aberration adjusted Gray map technique Gray map technique Hamming distance moment aberration threshold accepting algorithm uniform design

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Spatio-Spectral Compression of Hyperspectral Images 14

Generative Adversarial Networks for Spatio-Spectral Compress...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Fuchs, Martin Hermann Paul Byju, Akshara Preethy Walda, Alisa Rasti, Behnood Demir, Begum Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India Technische Universität Berlin Faculty of Electrical Engineering and Computer Science Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

ISBN: (纸本)9798331513139

Deep learning-based hyperspectral image (HSI) compression has recently attracted great attention in remote sensing due to the growth of hyperspectral data archives. Most of the existing models achieve either spectral or spatial compression and do not jointly consider the spatio-spectral redundancies present in HSIs. To address this problem, in this paper, we propose High Fidelity Compression (HiFiC)-based models for spatio-spectral compression of HSIs. In detail, we introduce two new models: i) HiFiC using Squeeze and Excitation (SE) blocks (denoted as HiFiCsE);and ii) HiFiC with 3D convolutions (denoted as HiFiC3D) in the framework of compression of HSIs. We analyze the effectiveness of HiFiCsE and HiFiC3D in compressing the spatio-spectral redundancies with channel attention and inter-dependency analysis. Experimental results show the efficacy of the proposed models in performing spatio-spectral compression, while reconstructing images at reduced bitrates with higher reconstruction quality. The code of the proposed models is publicly available at https://***/rsim/HSI-SSC. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Type-Representation Enhanced Event Detection via Structure Encoder 1

Type-Representation Enhanced Event Detection via Structure E...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Feng, Yuming Huang, Linmeng Liang, Haozhe Jin, Xiaolong Guan, Saiping Guo, Jiafeng School of Computer Science and Technology University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences Key Lab of Network Data Science and Technology China Institute of Systems Engineering Academy of Military Science Beijing China

ISBN: (纸本)9798350358780

Event detection, aiming to detect whether a sentence contains the type of events of interest, is one of the important tasks in information Extraction. There exist many methods for event detection, which usually treat event detection as a classification problem. These existing methods suffer from the imbalanced training data of different event types. To relieve this problem, this paper proposes a new Type-Representation-Enhanced Event Detection (TREED) method, which introduce hierarchical event type representations to enhance classification accuracy. Specifically, TREED first models the hierarchical relationship among event types in the dataset;Next, upon interactions between the representations of trigger words and event types, it obtains the new representations of trigger words integrating event type information. Finally, TREED classifies the events based on the obtained more accurate trigger word representations. Experimental results on a commonly used benchmark dataset, ACE-2005, demonstrate that the proposed model can improve both accuracy and recall of the event detection task. © 2023 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Aggregator Based Energy Aware RPL Routing for IoT Enabled Forest Environment

引用

Computers, Materials & Continua 2022年第8期72卷 4039-4055页

作者： S.Srividhya Suresh Sankaranarayanan Sergei A.Kozlov Joel J.P.C.Rodrigues Department of Data Science and Business Systems School of ComputingSRM Institute of Science and TechnologyChennai603203TamilnaduIndia Department of Networking and Communications School of ComputingSRM Institute of Science and TechnologyChennai603203TamilnaduIndia ITMO University St.PetersburgRussia Senac Faculty of Ceará FortalezaCEBrazil Instituto de Telecomunicações Covilhã6201-001Portugal

Forested areas are extremely vulnerable to disasters leading to environmental *** Fire is one among them which requires immediate *** are lot of works done by authors where Wireless Sensors and IoT have been used for forest fire ***,towards monitoring the forest fire and managing the energy efficiently in IoT,Energy Efficient Routing Protocol for Low power lossy networks(E-RPL)was *** were challenges about the scalability of the network resulting in a large end-to-end delay and less packet delivery which led to the development of Aggregator-based Energy Efficient RPL with data Compression(CAAERPL).Though CAA-ERPL proved effective in terms of reduced packet delivery,less energy consumption,and increased packet delivery ratio for varying number of nodes,there is still challenge in the selection of aggregator which is based purely on probability percentage of *** has been research work where fuzzy logic been employed for Mobile Ad-hoc Routing,RPL routing and cluster head selection in Wireless *** has been no work where fuzzy logic is employed for aggregator selection in Energy Efficient *** accordingly,we here have proposed Fuzzy Based Aggregator selection in Energy-efficient RPL for region thereby forming DODAG for communicating to Fog/*** here have developed fuzzy inference rules for selecting the aggregator based on strength which takes residual power,Node degree,and Expected Transmission Count(ETX)as input *** Fuzzy Aggregator Energy Efficient RPL(FA-ERPL)based on fuzzy inference rules were analysed against E-RPL in terms of scalability(First and Half Node die),Energy Consumption,and aggregator node energy *** the analysis,it was found that FA-ERPL performed better than *** were simulated using MATLAB and results.

关键词： Fuzzy logic aggregator IoT RPL routing wireless sensor network

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：