检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Yunke Wang Minjing Dong Yukun Zhao Bo Du Chang Xu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong China School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JARVIS-Leaderboard:a large scale benchmark of materials design methods

引用

npj Computational Materials 2024年第1期10卷 2280-2296页

作者： Kamal Choudhary Daniel Wines Kangming Li Kevin F.Garrity Vishu Gupta Aldo H.Romero Jaron T.Krogel Kayahan Saritas Addis Fuhr Panchapakesan Ganesh Paul R.C.Kent Keqiang Yan Yuchao Lin Shuiwang Ji Ben Blaiszik Patrick Reiser Pascal Friederich Ankit Agrawal Pratyush Tiwary Eric Beyerle Peter Minch Trevor David Rhone Ichiro Takeuchi Robert B.Wexler Arun Mannodi-Kanakkithodi Elif Ertekin Avanish Mishra Nithin Mathew Mitchell Wood Andrew Dale Rohskopf Jason Hattrick-Simpers Shih-Han Wang Luke E.K.Achenie Hongliang Xin Maureen Williams Adam J.Biacchi Francesca Tavazza Material Measurement Laboratory National Institute of Standards and TechnologyGaithersburgMD20899USA Department of Materials Science and Engineering University of Toronto27 King’s College CirTorontoONCanada Department of Electrical and Computer Engineering Northwestern UniversityEvanstonIL 60208USA Lewis-Sigler Institute for Integrative Genomics Princeton UniversityPrincetonNJ 08544USA Ludwig Institute for Cancer Research Princeton UniversityPrincetonNJ 08544USA Department of Physics and Astronomy West Virginia UniversityMorgantownWV 26506USA Materials Science and Technology Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Center for Nanophase Materials Science Oak Ridge National LaboratoryOak RidgeTN 37831USA Computational Sciences and Engineering Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Department of Computer Science and Engineering Texas A&M UniversityCollege StationTX 77843USA Globus University of ChicagoChicagoIL 60637USA Data Science and Learning Division Argonne National LabLemontIL 60439USA Institute of Nanotechnology Karlsruhe Institute of TechnologyKaiserstraße 1276131 KarlsruheGermany Institute of Theoretical Informatics Karlsruhe Institute of TechnologyKaiserstraße 1276131 KarlsruheGermany Department of Chemistry and Biochemistry and Institute for Physical Science and Technology University of MarylandCollege ParkMD 20742USA Department of Physics Applied Physics and AstronomyRensselaer Polytechnic InstituteTroyNY12180USA Department of Materials Science and Engineering University of MarylandCollege ParkMD20742USA Department of Chemistry and Institute of Materials Science and Engineering Washington University in St.LouisSt.LouisMO63130USA School of Materials Engineering Purdue UniversityWest LafayetteIN47907USA Department of Mechanical Science and Engineering University of Illinois Urbana-ChampaignUrbanaIllinois 61801USA Materials Research Laboratory University of Illinois Urbana-ChampaignUrbanaIL 61801USA Theore

Lack of rigorous reproducibility and validation are significant hurdles for scientific development across many *** science,in particular,encompasses a variety of experimental and theoretical approaches that require careful *** efforts have been developed previously to mitigate these ***,a comprehensive comparison and benchmarking on an integrated platform with multiple data modalities with perfect and defect materials data is still *** work introduces JARVIS-Leaderboard,an open-source and community-driven platform that facilitates benchmarking and enhances *** platform allows users to set up benchmarks with customtasks and enables contributions in the form of dataset,code,and meta-data *** cover the following materials design categories:Artificial Intelligence(ai),Electronic Structure(ES).

关键词： rigorous perfect enable

来源：评论

学校读者我要写书评

暂无评论

$V_{\text{cp}}$-Decomposition-Based Adaptive Search for Optimal Power Extraction in Photovoltaic Systems

引用

IEEE Transactions on Power Electronics 2024年第10期39卷 12794-12802页

作者： Jieming Ma Kangshi Wang Ming Huang Xiaoyang Chen Xingshuo Li Danny Hughes School of Advanced Technology AI University Research Center Xi'an Jiaotong-Liverpool University Suzhou China School of Electrical and Automation Engineering Nanjing Normal University Nanjing China Department of Computer Science EU Leuven Leuven Belgium

Maintaining optimal power in changing environments presents a significant challenge for photovoltaic systems. This article introduces a novel $V_{\text{cp}}$ decomposition-based adaptive strategy (VD-AS) aimed at enhancing optimal power extraction in varying environmental conditions. Distinct from the conventional maximum power point tracking (MPPT) technologies, the proposed VD-AS method estimates the peak pattern based on the voltage at the current peak on the power-voltage curve. Utilizing the peak pattern information, a sim-to-real peak identification model is capable of predicting the global maximum power point (GMPP) locus. It not only enables an accurate adaptive search for the GMPP locus, but also substantially minimizes the need for unnecessary global searches when the peak pattern is consistent. Experimental results from a laboratory prototype demonstrate that the proposed method can accurately track the GMPP with a smaller voltage search range and shorter tracking time. Its tracking efficiency is generally 10% higher than that of state-of-the-art GMPP tracking methods.

关键词： Tracking Adaptation models Voltage Optimization Current measurement Turning Photovoltaic systems

来源：评论

学校读者我要写书评

暂无评论

SELF-CLUSTERING GRAPH TRANSFORMER APPROACH TO MODEL RESTING STATE FUNCTIONAL BRaiN ACTIVITY

arXiv

引用

arXiv 2025年

作者： Thapaliya, Bishal Akbas, Esra Sapkota, Ram Ray, Bhaskar Calhoun, Vince Liu, Jingyu Department of Computer Science Georgia State University Atlanta United States Tri-Institutional Center for Translational Research in Neuroimaging and Data Science United States School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta United States

Resting-state functional magnetic resonance imaging (rs-fMRI) offers valuable insights into the human brain’s functional organization and is a powerful tool for investigating the relationship between brain function and cognitive processes as it allows for the functional organization of the brain to be captured without relying on a specific task or stimuli. In this study, we introduce a novel attention mechanism for graphs with subnetworks, named Self Clustering Graph Transformer (SCGT), designed to handle the issue of uniform node updates in graph transformers. By using static functional connectivity (FC) correlation features as input to the transformer model, SCGT effectively captures the sub-network structure of the brain by performing cluster-specific updates to the nodes unlike uniform node updates like vanilla graph transformers, further allowing us to learn and interpret the subclusters. We validate our approach on the Adolescent Brain Cognitive Development (ABCD) dataset, comprising 7,957 participants, for the prediction of total cognitive score and gender classification. Our results demonstrate that SCGT outperforms the vanilla graph transformer method, and other recent models, offering a promising tool for modeling brain functional connectivity and interpreting the underlying subnetwork structures. © 2025, CC BY.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Transformer-based functional time series modeling to unveil dynamic brain state transitions

Transformer-based functional time series modeling to unveil ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yurim Jang Jong Young Namgung Yeongjun Park Bo-Yong Park Artificial Intelligence Convergence Research Center Inha University Incheon Republic of Korea Department of Data Science Inha University Incheon Republic of Korea Department of Computer Engineering Inha University Incheon Republic of Korea Department of Data Science & Center for Neuroscience Imaging Research Inha University & Institute for Basic Science Incheon & Suwon Republic of Korea

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Brain state is dynamic in nature, and identifying the transitions between different brain states is crucial for understanding ongoing cognitive functions. Here, we opted for a transformer-based blood-oxygen-level-dependent transformer model (BolT) to investigate dynamic transitions of brain states across time. Using the given time series data, the model predicted subsequent time series. At the same time, it provided information about the contribution of each time point for the prediction with the importance weights. We extracted the time series corresponding to the top 10% and bottom 10% contribution of the importance weights. For each time series data, we constructed the connectivity matrix and calculated the degree centrality values. We compared the degree values between the top 10% and bottom 10% contribution data and found significant differences in the regions involved in the default mode network. Specifically, decreases in the degree values were observed at the highly contributed time points. Our findings indicate that the reorganization of connectome organization occurs in the default mode network during transitions in brain states.

关键词： Neuroscience Accuracy Time series analysis Organizations Predictive models Fasteners Brain modeling Transformers data models engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

Orthogonal matrix of polarization combinations:concept and application to multichannel holographic recording

引用

Opto-Electronic Advances 2024年第10期7卷 4-13页

作者： Shujun Zheng Jiaren Tan Hongjie Liu Xiao Lin Yusuke Saita Takanori Nomura Xiaodi Tan Information Photonics Research Center College of Photonic and Electronic EngineeringFujian Normal UniversityFuzhou 350117China Department of Electrical and Computer Engineering Duke UniversityDurhamNC 27708USA College of Photonic and Electronic Engineering Key Laboratory of Opto-Electronic Science and for Medicine of Ministry of EducationFujian Provincial Key Laboratory of Photonics TechnologyFujian Provincial Engineering Technology Research Center of Photoelectric Sensing ApplicationFujian Normal UniversityFuzhou 350117China Faculty of Systems Engineering Wakayama University930 SakaedaniWakayama640-8510Japan.

Orthogonal matrices have become a vital means for coding and signal processing owing to their unique distributional *** orthogonal matrices based on amplitude or phase combinations have been extensively explored,the orthogonal matrix of polarization combinations(OMPC)is a novel,relatively unexplored ***,we propose a method for constructing OMPCs of any dimension encompassing 4n(where n is 1,2,4,8,…)mutually orthogonal 2ncomponent polarization *** the field of holography,the integration of polarization multiplexing techniques with polarization-sensitive materials is expected to emerge as a groundbreaking approach for multichannel hologram multiplexing,offering considerable enhancements in data storage capacity and security.A multidimensional OMPC enables the realization of multichannel multiplexing and dynamical modulation of information in polarization holographic *** consolidating all information into a single position within the material,we effectively avoided extraneous crosstalk during the reconstruction *** results show that achieving four distinct holographic images individually and simultaneously depends on the polarization combination represented by the incident *** discovery opens up a new avenue for achieving highly holographic information storage and dynamically displayed information,harnessing the potential of OMPC to expand the heretofore limited dimensionality of orthogonal polarization.

关键词： orthogonal matrix of polarization combinations polarization-modulated multiplexing multichannel recording polarization holography dynamical information modulation

来源：评论

学校读者我要写书评

暂无评论

RFAConv: Innovating Spatial Attention and Standard Convolutional Operation

arXiv

引用

arXiv 2023年

作者： Zhang, Xin Liu, Chen Song, Tingting Yang, Degang Ye, Yichen Li, Ke Song, Yingze College of Computer and Information Science Chongqing Normal University China Chongqing Engineering Research Center of Educational Big Data Intelligent Perception and Application China College of Electronic and Information Engineering Southwest University China

Spatial attention has been widely used to improve the performance ofconvolutional neural networks. However, it has certain limitations. In thispaper, we propose a new perspective on the effectiveness of spatial attention,which is that the spatial attention mechanism essentially solves the problem ofconvolutional kernel parameter sharing. However, the information contained inthe attention map generated by spatial attention is not sufficient forlarge-size convolutional kernels. Therefore, we propose a novel attentionmechanism called Receptive-Field Attention (RFA). Existing spatial attention,such as Convolutional Block Attention Module (CBAM) and Coordinated Attention(CA) focus only on spatial features, which does not fully address the problemof convolutional kernel parameter sharing. In contrast, RFA not only focuses onthe receptive-field spatial feature but also provides effective attentionweights for large-size convolutional kernels. The Receptive-Field Attentionconvolutional operation (RFAConv), developed by RFA, represents a new approachto replace the standard convolution operation. It offers nearly negligibleincrement of computational cost and parameters, while significantly improvingnetwork performance. We conducted a series of experiments on ImageNet-1k, COCO,and VOC datasets to demonstrate the superiority of our approach. Of particularimportance, we believe that it is time to shift focus from spatial features toreceptive-field spatial features for current spatial attention mechanisms. Inthis way, we can further improve network performance and achieve even betterresults. The code and pre-trained models for the relevant tasks can be found athttps://***/Liuchen1997/RFAConv. © 2023, CC0.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Prognostic Phenotype Clustering of Uterine Sarcoma Patients

Prognostic Phenotype Clustering of Uterine Sarcoma Patients

引用

International Conference on e-health Networking, applications and Services (HealthCom)

作者： Tuao Zhang Suzhen Yuan Xue Zhou Wenwen Wang Xin Zhu Graduate School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Wuhan China Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Tokyo Japan

ISBN: (数字)9798350350548

ISBN: (纸本)9798350350555

Uterine sarcoma is a rare but highly aggressive malignancy with poor prognosis. In this study, prognostic pheno-types corresponding to the end point of mortality were explored by unsupervised machine learning (ML) on training $(\mathrm{n}=1985)$ and validation $(\mathrm{n}=498)$ datasets. The data were extracted from patients with uterine sarcoma in the Surveillance, Epidemiology, and End Results (SEER) database. A decision-making process of phenotype identification was performed and the findings were compared with existing research. Three phenotypes associated with stratified levels of mortality risks (high, intermediate and low) were identified. Kaplan-Meier survival analysis revealed significant differences among these phenotypes (pairwise comparison $p < 0.05$ ). The hazard ratio for mortality was 0.77 (95 % CI 0.68-0.88, $p < 0.001)$ between Phenotype 1 (high risk, $\mathrm{n}=673$ ) and Phenotype 3 (intermediate risk, $\mathrm{n}=631$ ), and 2.8 (95% CI 2.4-3.3, $p < 0.001)$ between Phenotype 2 (low risk, $\mathrm{n}=681$ ) and Phenotype 3. Furthermore, pathological grade, tumor size, and lymphatic node metastasis were identified as three critical predictive factors by comparing the distribution of risk factors among phenotypes. Without any priorities, ML effectively explored phenotypes that behave differently from data, offering a fresh viewpoint on prognostic prediction in uterine sarcoma.

关键词： Training Pathology Phenotypes Surveillance Mortality Machine learning Hazards Metastasis Prognostics and health management Tumors

来源：评论

学校读者我要写书评

暂无评论

Optimized Vision Transformer Training using GPU and Multi-threading

Optimized Vision Transformer Training using GPU and Multi-th...

引用

Artificial Intelligence (Cai), IEEE Conference on

作者： Jonathan Ledet Ashok Kumar Dominick Rizk Rodrigue Rizk KC Santosh Center for Advanced Computer Studies University of Louisiana at Lafayette Lafayette LA USA Department of Electrical Engineering and Computer Science Catholic University of America Washington DC USA Department of Computer Science Applied AI Research Lab University of South Dakota Vermillion SD USA

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Traditional Convolutional Neural Networks (CNNs) often struggle with capturing intricate spatial relationships and nuanced patterns in diverse datasets. To overcome these limitations, this work pioneers the application of Vision Transformer (ViT) models which have gained significant attention in the field of computer vision for their ability to capture long-range dependencies in images through self-attention mechanisms. However, training large-scale ViT models with a massive number of parameters poses computational challenges. In this paper, we present an optimized approach for training ViT models that leverages the parallel processing capabilities of Graphics Processing Units (GPUs) and optimizes the computational workload distribution using multi-threading. The proposed model is trained and tested on the CIFAR-10 dataset and achieved an outstanding accuracy of 99.92% after 100 epochs. The experimental results demonstrate the effectiveness of our approach in optimizing training efficiency compared to existing methods. This underscores the superior performance of ViT models and their potential to revolutionize image classification tasks.

关键词： Training computer vision Multithreading Computational modeling Neural networks Graphics processing units Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Our Way to Better Classifiers: Leveraging Synthetic data with Generative Models for Encrypted Network Traffic Classification

SSRN

引用

SSRN 2023年

作者： Zion, Yehonatan Hajaj, Chen Dvir, Amit Artzi, Gil Ben Mahpod, Shahar Dubin, Ran Department of Computer Science Ariel University Ariel Cyber Innovation Center Israel Department of Industrial Engineering & Management Data Science and Artificial Intelligence Research Center Ariel University Israel

Encrypted traffic classification has become a popular research topic due to the fact that it plays a vital part in Quality of Service (QoS), Quality of Experience (QoE), and network security. Moreover, by using ML-based and DL-based classification, it is possible to provide information without the need to decrypt it. While recent works have shown great innovation and contribution to the field, there is still a significant problem when it comes to the datasets in use. Most researchers use well-known open-source datasets that suffer from a lack of diversity (i.e., low number of classes or samples per class), which are quite often imbalanced. This paper aims to answer the question, "Is it possible to solve these datasets’ limitations by using generative models?" Specifically, we provide a survey of some known solutions in the field of generative models, assess their fit to the encrypted traffic classification domain, and evaluate their contribution to balancing the datasets and improving the classification metrics of different classifiers. Another contribution of this paper lies in the fact that we do not limit ourselves to the natural representation of network traffic as a time series. Since generative adversarial models (GANs) have proven to be very effective in the image processing domain, we transform the raw traffic data into an image representation of the signal. Our initial results, reported in this paper, show the applicability of such methods to an improvement of more than 30% in the accuracy of a network classification model by including synthetic samples generated by the GANs in their training set. © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

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：