检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Kitsak, Maksim Ganin, Alexander Elmokashfi, Ahmed Cui, Hongzhu Eisenberg, Daniel A. Alderson, David L. Korkin, Dmitry Linkov, Igor Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Network Science Institute Northeastern University BostonMA02115 United States Department of Systems and Information Engineering University of Virginia CharlottesvilleVA22904 United States U.S. Army Engineer Research and Development Center Contractor Concord MA01742 United States Simula Metropolitan Center for Digital Engineering Oslo Norway Bioinformatics and Computational Biology Program Worcester Polytechnic Institute WorcesterMA01609 United States Institute for Genomic Medicine Columbia University Medical Center New YorkNY United States Operations Research Department Naval Postgraduate School MontereyCA93943 United States Data Science Program Worcester Polytechnic Institute WorcesterMA01609 United States Computer Science Department Worcester Polytechnic Institute WorcesterMA01609 United States U.S. Army Engineer Research and Development Center Environmental Laboratory Concord MA01742 United States

Dynamic processes on networks, be it information transfer in the Internet, contagious spreading in a social network, or neural signaling, take place along shortest or nearly shortest paths. Unfortunately, our maps of most large networks are substantially incomplete due to either the highly dynamic nature of networks, or high cost of network measurements, or both, rendering traditional path finding methods inefficient. We find that shortest paths in large real networks, such as the network of protein-protein interactions (PPI) and the Internet at the autonomous system (AS) level, are not random but are organized according to latent-geometric rules. If nodes of these networks are mapped to points in latent hyperbolic spaces, shortest paths in them align along geodesic curves connecting endpoint nodes. We find that this alignment is sufficiently strong to allow for the identification of shortest path nodes even in the case of substantially incomplete networks. We demonstrate the utility of latent-geometric path finding in problems of cellular pathway reconstruction and communication security. Copyright © 2022, The Authors. All rights reserved.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Weisfeiler and Leman go Machine Learning: The Story so far

arXiv

引用

arXiv 2021年

作者： Morris, Christopher Lipman, Yaron Maron, Haggai Rieck, Bastian Kriege, Nils M. Grohe, Martin Fey, Matthias Borgwardt, Karsten Department of Computer Science RWTH Aachen University Aachen Germany Meta AI Research Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel NVIDIA Research Tel Aviv Israel AIDOS Lab Institute of AI for Health Helmholtz Zentrum München and Technical University of Munich Munich Germany Faculty of Computer Science University of Vienna Vienna Austria Research Network Data Science University of Vienna Vienna Austria Kumo.AI Mountain ViewCA United States Machine Learning & Computational Biology Lab Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland

In recent years, algorithms and neural architectures based on the Weisfeiler–Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm’s use in a machine-learning setting, focusing on the supervised regime. We discuss the theoretical background, show how to use it for supervised graph and node representation learning, discuss recent extensions, and outline the algorithm’s connection to (permutation-)equivariant neural architectures. Moreover, we give an overview of current applications and future directions to stimulate further research. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Predicting risk of cardiovascular disease using retinal optical coherence tomography imaging

arXiv

引用

arXiv 2024年

作者： Maldonado-Garcia, Cynthia Bonazzola, Rodrigo Ferrante, Enzo Julian, Thomas H. Sergouniotis, Panagiotis I. Ravikumar, Nishant Frangi, Alejandro F. Centre for Computational Imaging and Simulation Technologies in Biomedicine School of Computing University of Leeds Leeds United Kingdom CONICET-UNL Santa Fe Argentina Division of Evolution Infection and Genomics School of Biological Sciences Faculty of Biology Medicine and Health University of Manchester Manchester United Kingdom Manchester Royal Eye Hospital Manchester University NHS Foundation Trust Manchester United Kingdom Manchester Centre for Genomic Medicine Saint Mary’s Hospital Manchester University NHS Foundation Trust Manchester United Kingdom Wellcome Genome Campus Cambridge United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences Faculty of Biology Medicine and Health University of Manchester Manchester United Kingdom School of Computer Science Faculty of Science and Engineering University of Manchester Kilburn Building Manchester United Kingdom Christabel Pankhurst Institute University of Manchester Manchester United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom

Cardiovascular diseases (CVD) are the leading cause of death globally. Non-invasive, cost-effective imaging techniques play a crucial role in early detection and prevention of CVD. Optical coherence tomography (OCT) has gained recognition as a potential tool for early CVD risk prediction, though its use remains underexplored. In this study, we investigated the potential of OCT as an additional imaging technique to predict future CVD events. We analysed retinal OCT data from the UK Biobank. The dataset included 612 patients who suffered a myocardial infarction (MI) or stroke within five years of imaging and 2,234 controls without CVD (total: 2,846 participants). A self-supervised deep learning approach based on Variational Autoencoders (VAE) was used to extract low-dimensional latent representations from high-dimensional 3D OCT images, capturing distinct features of retinal layers. These latent features, along with clinical data, were used to train a Random Forest (RF) classifier to differentiate between patients at risk of future CVD events (MI or stroke) and healthy controls. Our model achieved an AUC of 0.75, sensitivity of 0.70, specificity of 0.70, and accuracy of 0.70, outperforming the QRISK3 score (the third version of the QRISK cardiovascular disease risk prediction algorithm;AUC = 0.60, sensitivity = 0.60, specificity = 0.55, accuracy = 0.55). The choroidal layer in OCT images was identified as a key predictor of future CVD events, revealed through a novel model explainability approach. This study demonstrates that retinal OCT imaging is a cost-effective, non-invasive alternative for predicting CVD risk, offering potential for widespread application in optometry practices and hospitals. © 2024, CC BY-NC-ND.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Model Interpretability through the lens of computational complexity

arXiv

引用

arXiv 2020年

作者： Barceló, Pablo Monet, Mikaël Pérez, Jorge Roa, Bernardo Anibal Subercaseaux Institute for Mathematical and Computational Engineering PUC Chile Inria Lille France Department of Computer Science Universidad de Chile Chile Millennium Institute for Foundational Research on Data Chile

In spite of several claims stating that some models are more interpretable than others – e.g., "linear models are more interpretable than deep neural networks" – we still lack a principled notion of interpretability to formally compare among different classes of models. We make a step towards such a notion by studying whether folklore interpretability claims have a correlate in terms of computational complexity theory. We focus on local post-hoc explainability queries that, intuitively, attempt to answer why individual inputs are classified in a certain way by a given model. In a nutshell, we say that a class C1 of models is more interpretable than another class C2, if the computational complexity of answering post-hoc queries for models in C2 is higher than for those in C1. We prove that this notion provides a good theoretical counterpart to current beliefs on the interpretability of models;in particular, we show that under our definition and assuming standard complexity-theoretical assumptions (such as P ≠ NP), both linear and tree-based models are strictly more interpretable than neural networks. Our complexity analysis, however, does not provide a clear-cut difference between linear and tree-based models, as we obtain different results depending on the particular post-hoc explanations considered. Finally, by applying a finer complexity analysis based on parameterized complexity, we are able to prove a theoretical result suggesting that shallow neural networks are more interpretable than deeper ones. Copyright © 2020, The Authors. All rights reserved.

关键词： computational complexity

来源：评论

学校读者我要写书评

暂无评论

On Aggregation in Ensembles of Multilabel Classifiers

arXiv

引用

arXiv 2020年

作者： Nguyen, Vu-Linh Hüllermeier, Eyke Rapp, Michael Mencía, Eneldo Loza Fürnkranz, Johannes Heinz Nixdorf Institute Department of Computer Science Paderborn University Germany Knowledge Engineering Group TU Darmstadt Germany Computational Data Analytics Group JKU Linz Austria

While a variety of ensemble methods for multilabel classification have been proposed in the literature, the question of how to aggregate the predictions of the individual members of the ensemble has received little attention so far. In this paper, we introduce a formal framework of ensemble multilabel classification, in which we distinguish two principal approaches: "predict then combine" (PTC), where the ensemble members first make loss minimizing predictions which are subsequently combined, and "combine then predict" (CTP), which first aggregates information such as marginal label probabilities from the individual ensemble members, and then derives a prediction from this aggregation. While both approaches generalize voting techniques commonly used for multilabel ensembles, they allow to explicitly take the target performance measure into account. Therefore, concrete instantiations of CTP and PTC can be tailored to concrete loss functions. Experimentally, we show that standard voting techniques are indeed outperformed by suitable instantiations of CTP and PTC, and provide some evidence that CTP performs well for decomposable loss functions, whereas PTC is the better choice for non-decomposable losses. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Accelerated MRI reconstruction with separable and enhanced low-rank Hankel regularization

arXiv

引用

arXiv 2021年

作者： Zhang, Xinlin Lu, Hengfa Guo, Di Lai, Zongying Ye, Huihui Peng, Xi Zhao, Bo Qu, Xiaobo Biomedical Intelligent Cloud R&D Center Department of Electronic Science National Institute for Data Science in Health and Medicine Xiamen University Xiamen361105 China The Department of Biomedical Engineering University of Texas at Austin AustinTX78712 United States The School of Computer and Information Engineering Xiamen University of Technology Xiamen361021 China The School of Information Engineering Jimei University Xiamen361024 China The State of Key Laboratory of Modern Optical Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou310058 China The Department of Radiology Mayo Clinic RochesterMN55902 United States The Department of Biomedical Engineering Oden Institute for Computational Engineering and Sciences University of Texas at Austin AustinTX78712 United States

The combination of the sparse sampling and the low-rank structured matrix reconstruction has shown promising performance, enabling a significant reduction of the magnetic resonance imaging data acquisition time. However, the low-rank structured approaches demand considerable memory consumption and are time-consuming due to a noticeable number of matrix operations performed on the huge-size block Hankel-like matrix. In this work, we proposed a novel framework to utilize the low-rank property but meanwhile to achieve faster reconstructions and promising results. The framework allows us to enforce the low-rankness of Hankel matrices constructing from 1D vectors instead of 2D matrices from 1D vectors and thus avoid the construction of huge block Hankel matrix for 2D k-space matrices. Moreover, under this framework, we can easily incorporate other information, such as the smooth phase of the image and the low-rankness in the parameter dimension, to further improve the image quality. We built and validated two models for parallel and parameter magnetic resonance imaging experiments, respectively. Our retrospective in-vivo results indicate that the proposed approaches enable faster reconstructions than the state-of-the-art approaches, e.g., about 8× faster than STDLR-SPIRiT, and faithful removal of undersampling artifacts. Copyright © 2021, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Comparison and Evaluation of Methods for a Predict+Optimize Problem in Renewable Energy

arXiv

引用

arXiv 2022年

作者： Bergmeir, Christoph de Nijs, Frits Sriramulu, Abishek Abolghasemi, Mahdi Bean, Richard Betts, John Bui, Quang Dinh, Nam Trong Einecke, Nils Esmaeilbeigi, Rasul Ferraro, Scott Galketiya, Priya Genov, Evgenii Glasgow, Robert Godahewa, Rakshitha Kang, Yanfei Limmer, Steffen Magdalena, Luis Montero-Manso, Pablo Peralta, Daniel Kumar, Yogesh Pipada Sunil Rosales-Pérez, Alejandro Ruddick, Julian Stratigakos, Akylas Stuckey, Peter Tack, Guido Triguero, Isaac Yuan, Rui Department of Data Science and Artificial Intelligence Monash University Melbourne Australia School of Mathematics and Physics University of Queensland Brisbane Australia Centre for Energy Data Innovation School of Information Technology and Electrical Engineering University of Queensland Brisbane Australia School of Electrical and Electronics Engineering University of Adelaide Adelaide Australia Honda Research Institute Europe GmbH Offenbach am Main63073 Germany School of Information Technology Deakin University Melbourne Australia Building and Property Division Monash University Melbourne Australia EVERGi MOBI Vrije Universiteit Brussel Brussels Belgium School of Economics and Management Beihang University Beijing China E.T.S. Ingenieros Informáticos Universidad Politécnica de Madrid Madrid28660 Spain Disciple of Business Analytics University of Sydney Australia IDLab Department of Information Technology Ghent University - imec Belgium Department of Computer Science Centro de Investigación en Matem áticas Monterrey66629 Mexico Mines Paris PSL University Sophia Antipolis06904 France DaSCI Andalusian Institute in Data Science and Computational Intelligence Granada Spain Department of Computer Science and Artificial Intelligence University of Granada Granada Spain

Algorithms that involve both forecasting and optimization are at the core of solutions to many difficult real-world problems, such as in supply chains (inventory optimization), traffic, and in the transition towards carbon-free energy generation in battery/load/production scheduling in sustainable energy systems. Typically, in these scenarios we want to solve an optimization problem that depends on unknown future values, which therefore need to be forecast. As both forecasting and optimization are difficult problems in their own right, relatively few research has been done in this area. This paper presents the findings of the "IEEE-CIS Technical Challenge on Predict+Optimize for Renewable Energy Scheduling," held in 2021. We present a comparison and evaluation of the seven highest-ranked solutions in the competition, to provide researchers with a benchmark problem and to establish the state of the art for this benchmark, with the aim to foster and facilitate research in this area. The competition used data from the Monash Microgrid, as well as weather data and energy market data. It then focused on two main challenges: forecasting renewable energy production and demand, and obtaining an optimal schedule for the activities (lectures) and on-site batteries that lead to the lowest cost of energy. The most accurate forecasts were obtained by gradient-boosted tree and random forest models, and optimization was mostly performed using mixed integer linear and quadratic programming. The winning method predicted different scenarios and optimized over all scenarios jointly using a sample average approximation method. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Physical Publicly Verifiable Randomness from Pulsars

arXiv

引用

arXiv 2022年

作者： Dawson, Joanne R. Hobbs, George Gao, Yansong Camtepe, Seyit Pieprzyk, Josef Feng, Yi Tranfa, Luke Bradbury, Sarah Zhu, Weiwei Li, Di CSIRO Space and Astronomy Australia Telescope National Facility PO Box 76 EppingNSW1710 Australia Department of Physics and Astronomy MQ Research Centre in Astronomy Astrophysics and Astrophotonics Macquarie University NSW2109 Australia School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China CSIRO Data61 PO Box 76 EppingNSW1710 Australia Institute of Computer Science Polish Academy of Sciences Poland National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China University of Chinese Academy of Sciences Beijing100049 China BrisbaneQLD4001 Australia NAOC-UKZN Computational Astrophysics Centre University of KwaZulu-Natal Durban4000 South Africa

We demonstrate how radio pulsars can be used as random number generators. Specifically, we focus on publicly verifiable randomness (PVR), in which the same sequence of trusted and verifiable random numbers is obtained by multiple parties. PVR is a critical building block for many processes and algorithms (including cryptography, scientific trials, electoral audits and international treaties). However, current approaches (based on number theory) may soon become vulnerable to quantum computers, motivating a growing demand for PVR based on natural physical phenomena. In this context, we explore pulsars as a potential physical PVR source. We first show that bit sequences extracted from the measured flux densities of a bright millisecond pulsar can pass standardised tests for randomness. We then quantify three illustrative methods of bit-extraction from pulsar flux density sequences, using simultaneous observations of a second pulsar carried out with the Parkes telescope in Australia and the Five-hundred-metre Aperture Spherical radio Telescope (FAST) in China, supported by numerical simulations. We demonstrate that the same bit sequence can indeed be obtained at both observatories, but the ubiquitous presence of radiometer noise needs to be accounted for when determining the expected bit error rate between two independent sequences. We discuss our results in the context of an imaginary use-case in which two mutually distrusting parties wish to obtain the same random bit sequence, exploring potential methods to mitigate against a malicious participant. © 2022, CC BY-NC-ND.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Model interpretability through the lens of computational complexity 20

Model interpretability through the lens of computational com...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Pablo Barceló Mikaël Monet Jorge Pérez Bernardo Subercaseaux Institute for Mathematical and Computational Engineering PUC-Chile and Millennium Institute for Foundational Research on Data Chile Inria Lille France Department of Computer Science Universidad de Chile and Millennium Institute for Foundational Research on Data Chile

ISBN: (纸本)9781713829546

In spite of several claims stating that some models are more interpretable than others - e.g., "linear models are more interpretable than deep neural networks" - we still lack a principled notion of interpretability to formally compare among different classes of models. We make a step towards such a notion by studying whether folklore interpretability claims have a correlate in terms of computational complexity theory. We focus on local post-hoc explainability queries that, intuitively, attempt to answer why individual inputs are classified in a certain way by a given model. In a nutshell, we say that a class Ƈ1 of models is more interpretable than another class Ƈ2, if the computational complexity of answering post-hoc queries for models in Ƈ2 is higher than for those in Ƈ1. We prove that this notion provides a good theoretical counterpart to current beliefs on the interpretability of models; in particular, we show that under our definition and assuming standard complexity-theoretical assumptions (such as P ≠ NP), both linear and tree-based models are strictly more interpretable than neural networks. Our complexity analysis, however, does not provide a clear-cut difference between linear and tree-based models, as we obtain different results depending on the particular post-hoc explanations considered. Finally, by applying a finer complexity analysis based on parameterized complexity, we are able to prove a theoretical result suggesting that shallow neural networks are more interpretable than deeper ones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A causal lens for peeking into black box predictive models: Predictive model interpretation via causal attribution

arXiv

引用

arXiv 2020年

作者： Khademi, Aria Honavar, Vasant Artificial Intelligence Research Laboratory College of Information Sciences and Technology United States Department of Computer Science and Engineering Institute of Computational and Data Sciences Pennsylvania State University United States

With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing need for effective techniques for explaining such models and their predictions. We aim to address this problem in settings where the predictive model is a black box;That is, we can only observe the response of the model to various inputs, but have no knowledge about the internal structure of the predictive model, its parameters, the objective function, and the algorithm used to optimize the model. We reduce the problem of interpreting a black box predictive model to that of estimating the causal effects of each of the model inputs on the model output, from observations of the model inputs and the corresponding outputs. We estimate the causal effects of model inputs on model output using variants of the Rubin Neyman potential outcomes framework for estimating causal effects from observational data. We show how the resulting causal attribution of responsibility for model output to the different model inputs can be used to interpret the predictive model and to explain its predictions. We present results of experiments that demonstrate the effectiveness of our approach to the interpretation of black box predictive models via causal attribution in the case of deep neural network models trained on one synthetic data set (where the input variables that impact the output variable are known by design) and two real-world data sets: Handwritten digit classification, and Parkinson’s disease severity prediction. Because our approach does not require knowledge about the predictive model algorithm and is free of assumptions regarding the black box predictive model except that its input-output responses be observable, it can be applied, in principle, to any black box predictive model. Copyright © 2020, 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

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：