检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Chen, Yinsong Yu, Samson S. Li, Zhong Eshraghian, Jason K. Lim, Chee Peng School of Engineering Deakin University MelbourneVIC3216 Australia Faculty of Mathmatics and Computer Science FernUniversität Hagen58084 Germany Department of Electrical and Computer Engineering University of California Santa CruzCA95064 United States Department of Computing Technologies Swinburne University of Technology HawthornVIC3122 Australia

While deep learning models have seen significant success across various domains, their black-box learning nature and lack of interpretability affect their reliability in safety-critical applications like medical diagnostics and autonomous vehicles. In an attempt to address these limitations, Bayesian neural networks (BNNs) offer a promising alternative by incorporating uncertainty estimation into model predictions, enhancing transparency and decision-making. However, BNN development has primarily focused on efficient, high-fidelity approximate inference and guaranteed convergence in asymptotic settings. These are unsuitable for modern high-dimensional, multimodal, and non-asymptotic deep learning applications, undermining their theoretical advantages. To bridge this gap, this paper provides in-depth reviews on how approximate Bayesian inference leverages deep learning optimization to achieve high efficiency and fidelity in high-dimensional spaces and multimodal loss landscapes. It also reconciles Bayesian consistency with generalization objectives in non-asymptotic settings and investigates the generalization capabilities of BNNs. Additionally, this survey examines the often-overlooked expressiveness of BNNs, emphasizing how weight uncertainty and the absence of in-between uncertainty affect their performance. This survey aims to inspire BNN practitioners to adopt a deep learning perspective and offer valuable insights to propel further advancements in the field. © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LARGE DEVIATIONS AND MODERATE DEVIATIONS FOR SUMS OF NEGATIVELY DEPENDENT RANDOM VARIABLES

引用

Acta Mathematica Scientia 2011年第1期31卷 344-352页

作者：刘莉万成高冯艳钦 School of Mathematics and Statistics Wuhan University School of Mathmatics and Computer Science Hubei University

In this article, we obtain the large deviations and moderate deviations for negatively dependent （ND） and non-identically distributed random variables defined on （-∞, ＋∞）. The results show that for some non-identical random variables, precise large deviations and moderate deviations remain insensitive to negative dependence structure.

关键词： Large deviation moderate deviation negative dependence non-identical distribution

来源：评论

学校读者我要写书评

暂无评论

Introducing QuantConn: Overcoming Challenging Diffusion Acquisitions with Harmonization 15th

Introducing QuantConn: Overcoming Challenging Diffusion Acqu...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Newlin, Nancy Schilling, Kurt Koudoro, Serge Chandio, Bramsh Qamar Kanakaraj, Praitayini Moyer, Daniel Kelly, Claire E. Genc, Sila Yang, Joseph Yuan-Mou Wu, Ye Adluru, Nagesh Nath, Vishwesh Pathak, Sudhir Schneider, Walter Gade, Anurag Consagra, William Rathi, Yogesh Hendriks, Tom Vilanova, Anna Chamberland, Maxime Pieciak, Tomasz Ciupek, Dominika Vega, Antonio Tristán Aja-Fernández, Santiago Malawski, Maciej Ouedraogo, Gani Machnio, Julia Thompson, Paul M. Jahanshad, Neda Garyfallidis, Eleftherios Landman, Bennett Department of Computer Science Vanderbilt University NashvilleTN United States Department of Radiology and Radiological Sciences Vanderbilt University Medical Center Nashville United States Indiana University Bloomington BloomingtonIN United States Mark and Mary Stevens Neuroimaging and Informatics Institute Keck School of Medicine of USC Los AngelesCA United States Developmental Imaging Murdoch Children’ Research Institute Melbourne Australia Murdoch Children’s Research Institute Melbourne Australia Turner Institute for Brain and Mental Health School of Psychological Sciences Monash University Melbourne Australia Department of Neurosurgery Royal Children’s Hospital Melbourne Australia Neuroscience Research Murdoch Children’s Research Institute Melbourne Australia Department of Paediatrics University of Melbourne Melbourne Australia School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Waisman Center Department of Radiology University of Wisconsin Madison United States NVIDIA Santa Clara United States Learning Research and Development Center University of Pittsburgh Pittsburgh United States Brigham and Women’s Hospital Boston United States Brigham and Women’s Hospital Harvard Medical School Boston United States Department of Computer Science and Mathmatics Eindhoven University of Technology Eindhoven Netherlands LPI ETSI Telecomunicación Universidad de Valladolid Castilla y León Spain Sano Centre for Computational Medicine Kraków30-054 Poland Aix-Marseille Université Marseille France Vanderbilt University Institute of Imaging Science Vanderbilt University NashvilleTN United States Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States

ISBN: (纸本)9783031869198

White matter alterations are increasingly implicated in neurological diseases and their progression. Diffusion-weighted magnetic resonance imaging (DW-MRI) has been included in many international-scale studies to identify alterations in white matter microstructure and connectivity. Yet, quantitative investigation of DW-MRI data is hindered by a lack of consistency due to variations in acquisition protocols, sites, and scanners. Specifically, there is a need to harmonize the preprocessing of DW-MRI datasets to ensure that compatible and reproducible quantitative metrics are derived from each site, including (1) bundle-wise microstructure measures, (2) features of white matter fiber bundles, and (3) connectomics measures. In the MICCAI CDMRI 2023 QuantConn challenge, participants are provided raw data from the same individuals taken with two different acquisition protocols on a single 4 tesla scanner in the same scanning session and asked to preprocess the data in order to minimize acquisition differences while retaining biological variation. Here, we outline the testing framework, provide baseline pre-harmonized results, and discuss the learning implications of this challenge. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Investigation of future applications of self-engineering using drones

引用

Materials Today: Proceedings 2022年 64卷 1255-1260页

作者： Tahir Naz, Ayesha Brooks, Sam Roy, Rajkumar School of Mathmatics Computer Science and Engineering City Univeristy of London Northhampton Square London United Kingdom

Self-engineering (SE) systems aim to autonomously respond to a loss of function and take action to return functionality. Recently there have been a number of demonstrations of SE using multi-rotor drones to inspect and repair systems (such as repairing potholes), though many of these systems do not meet all the requirements of a SE system. This research identifies and explores new ideas for SE where drones could be utilised. Five ideas were successfully identified from consultations with experts and authors. The five ideas created are: 1) self-repair in enclosed spaces of ships, 2) self-cleaning roads, 3) self-repairing air conditioning systems, 4) autonomous underwater pipe repair, and 5) self-repair of damaged building cladding. Possible inspection and repair actions that a drone could perform are identified for each proposed system. From a short industry survey and further interviews, idea 1) (self-repair in enclosed spaces) was identified as the most promising for future development. The potential cost of building the system is discussed at the end of the paper;however, detailed cost estimation is too uncertain because of the difficulty in estimating the cost of developing autonomous capabilities. © 2022

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Multi-feature PM2.5 Prediction with ARIMA-LSTM

Multi-feature PM2.5 Prediction with ARIMA-LSTM

引用

2022 International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2022

作者： Xiao, Junwei Wang, Qingfang Cui, Jiawang Yu, Jing School of Mathmatics and Computer Science Whpu Wuhan China

ISBN: (数字)9781665498586

ISBN: (纸本)9781665498586

One of the most harmful environmental risk to human health is air pollution. Effective prediction of pollutants in the air is conducive to air improvement and pollution control. Air quality data has the characteristics of instability and nonlinear, to more accurate prediction of pollutants. The ARIMA-LSTM model is applied to forecast PM2.5 content in a continuous-Time in us paper. The data provided is time-series data, so we use LSTM for processing. The traditional prediction method has many limitations. It can not take all aspects into account in the multi-feature aspect, and the accuracy is not so accurate. We use the ARIMA model to deal with linear and nonlinear problems in the LSTM model. LSTM is an optimal model for predicting time series, but the data used have multiple characteristic values, which has no significant effect on seasonal prediction and trend prediction. The result shows our prediction model performs better than other models in our paper. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

An energy considering RBAC model for wireless sensor network

An energy considering RBAC model for wireless sensor network

引用

7th International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2011

作者： Song, Wen Zhao, Wu Lei, Yuan Wei, Xiong School of Mathmatics and Computer Science Xiangfan University Xiangfan China

ISBN: (纸本)9781424462520

RBAC (Role Based Access Control) model was extended in theory and a special RBAC for wireless sensor network based on energy considerations was proposed. The core modules, levels of roles and restriction mechanisms are described and defined in detail for the model. For different wireless sensor network architectures, the appropriate mechanisms were designed. Finally, theoretical analysis and evaluation of the model and the model is fesible and practial for wireless sensor network. © 2011 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Digital Image Processing Using Noise Removal Technique: A Non-Linear Approach

Digital Image Processing Using Noise Removal Technique: A No...

引用

2022 IEEE Asia-Pacific Conference on computer science and Data Engineering, CSDE 2022

作者： Chand, Rishal Ravikesh Farik, Mohammed Sharma, Neeraj Anand School of Science and Technology The University of Fiji Department of Computer Science and Mathmatics Fiji

ISBN: (纸本)9781665453059

An undesirable by-product of a captured image is Image Noise-random distribution of brightness and color misinformation. Denoising is one of the common components which is present in digital image processing techniques, Image processing has become an integral part of today's era amongst rapidly growing technologies. The process of manipulating images by using various algorithms exploring techniques to pre-process an image, improving its pictorial information for human interpretation. This research paper explores different types of image noise that can be present in a digital image and degradation by photo electronic noise, impulse (salt & pepper) noise and gaussian noise, thus reviews on linear approaches to denoise the image using 2D convolution filters and median non-linear filters. © 2022 IEEE.

关键词： Salt and pepper noise

来源：评论

学校读者我要写书评

暂无评论

A new Model for a Remote Connection with Hardware Devices using Javascript

引用

IFAC-PapersOnLine 2016年第6期49卷 133-137页

作者： Sáenz, J. Esquembre, F. García, F.J. Torre, L. de la Dormido, S. Departament of Informatics and Automatics Computer Science School UNED Spain Mathmatics Faculty Universidad de Murcia Campus Espinardo Murcia Spain Departament of Computer Engineering and Technology Informatics Faculty Campus Espinardo Murcia Spain

Nowadays online resources play an important role in teaching and learning thanks to new advances in technology. This importance is enhanced in scientific areas and even more for distance education universities, where the classic hands-on laboratories are not always possible. For that reason, these face-to-face laboratory practices have been replaced or even complemented with online virtual and remote laboratories (VRL). Normally, these applications are developed with high level programming tools, and these, to greater or lesser extent, use Java. Unfortunately, the newly discovered Java security issues and the impossibility to run Java in smart devices are restrictions to the dissemination of this kind of applications. This work is the first step towards get a new structure to Easy Java/Javascript Simulations (EjsS) that allows a remote connection with hardware devices using javascript. In this regard, the first objective is to solve the problems with Java applications when using EjsS. The proposed solution provides the user a structure to reuse their VRLs using a Java model that runs in a server and a Javascript graphical user interface in the client device. © 2016

关键词： Distance education computer aided software engineering computer hardware computer software Control engineering Distributed computer systems Graphical user interfaces Hardware High level languages Laboratories Hands on laboratories Hardware devices High level programming Java applications Laboratory practices Online resources Remote laboratories Teaching and learning

来源：评论

学校读者我要写书评

暂无评论

Improved prediction of HIV-1 protease genotypic resistance testing assays using a consensus technique

Improved prediction of HIV-1 protease genotypic resistance t...

引用

International Joint Conference on Neural Networks 2006, IJCNN '06

作者： Thomas, Alex C. Zheng, Rong Yang School of Engineering Computer Science and Mathmatics University of Exeter Exeter EX4 4QF United Kingdom

ISBN: (纸本)0780394909

Mutations in HIV-1 drug targets can cause reduced affinity to antiretroviral inhibitors, leading to the emergence of resistant variants resulting in failure of treatment in infected individuals. Resistance testing is an important factor in the continued success of viral therapy. We found that through combining a structural based computational docking method and a classic machine learning technique we could create a consensus system capable of improving the prediction accuracy by 5.56% over either method used individually. The result was the creation of a genotypic resistance testing approach capable of classifying a wider cross-section of strains, hence making it a more accurate resistance testing method. © 2006 IEEE.

关键词： Bioassay

来源：评论

学校读者我要写书评

暂无评论

The Number of Solutions of Certain Equations over Finite Fields

引用

Wuhan University Journal of Natural sciences 2022年第1期27卷 49-52页

作者： HU Shuangnian LIU Jianghan QIN Zhentao School of Mathematics and Statistics Nanyang Institute of TechnologyNanyang 473004HenanChina College of Computer and Information Science Southwest UniversityChongqing 400715China School of Mathmatics and Computer Panzhihua UniversityPanzhihua 617000SichuanChina

Let s be a positive integer,p be an odd prime,q=p^(s),and let F_(q)be a finite field of q *** N_(q)be the number of solutions of the following equations:(x_(1)^(m_(1))+x_(2)^(m_(2))+…+x_(n)^(m_(n)))^(k)=x_(1)x_(2)…x_(n)x^(k_(n+1))_(n+1)…x^(k_(t))_(t)over the finite field F_(q),with n≥2,t>n,k,and k_(j)(n+1≤j≤t),m_(i)(1≤i≤n)are positive *** this paper,we find formulas for N_(q)when there is a positive integer l such that dD|(p^(l)+1),where D=1 cm[d_(1),…,d_(n)],d=gcd(n∑i=1M/m_(i)-kM,(q-1)/D),M=1 cm[m_(1),…,m_(n)],d_(j)=gcd(m_(j),q-1),1≤j≤*** we determine N_(q)explicitly under certain *** extends Markoff-Hurwitz-type equations over finite field.

关键词： finite field rational point diagonal equation Markoff-Hurwitz-type equations

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：