检索结果-内蒙古大学图书馆

37th International Conference on Machine Learning, ICML 2020

作者： Nazarov, Ivan Burnaev, Evgeny Centre for Data Intensive Sciecne and Engineering Skolkovo Insitiute of Science and Technology Msocow Russia

ISBN: (纸本)9781713821120

With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural representation in the complex domain. To this end we extend Sparse Variational Dropout to complex-valued neural networks and verify the proposed Bayesian technique by conducting a large numerical study of the performance-compression trade-off of C-valued networks on two tasks: image recognition on MNIST-like and CIFAR10 datasets and music transcription on MusicNet. We replicate the state-of-the-art result by Trabelsi et al. (2018) on MusicNet with a complex-valued network compressed by 50 − 100× at a small performance penalty. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Medical history predicts phenome-wide disease onset and enables the rapid response to emerging health threats (vol 16, 585, 2025)

引用

NATURE COMMUNICATIONS 2025年第1期16卷 1-15页

作者： Steinfeldt, Jakob Wild, Benjamin Buergel, Thore Pietzner, Maik Upmeier zu Belzen, Julius Vauvelle, Andre Hegselmann, Stefan Denaxas, Spiros Hemingway, Harry Langenberg, Claudia Landmesser, Ulf Deanfield, John Eils, Roland Department of Cardiology Angiology and Intensive Care Medicine Deutsches Herzzentrum der Charité (DHZC) Berlin Germany Charité – Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin Klinik/Centrum Berlin Germany Computational Medicine Berlin Institute of Health (BIH) Charite - University Medicine Berlin Berlin Germany Friede Springer Cardiovascular Prevention Center@Charite Charite - University Medicine Berlin Berlin Germany Institute of Cardiovascular Sciences University College London London UK Berlin Institute of Health (BIH) Charite - University Medicine Berlin Berlin Germany DZHK (German Centre for Cardiovascular Research) Partner Site Berlin Berlin Berlin Germany MRC Epidemiology Unit Institute of Metabolic Science University of Cambridge Cambridge UK Precision Health University Research Institute Queen Mary University of London and Barts NHS Trust London UK Center for Digital Health Berlin Institute of Health (BIH) Charite - University Medicine Berlin Berlin Germany Health Data Science Unit Heidelberg University Hospital and BioQuant Heidelberg Germany Institute of Health Informatics University College London London UK British Heart Foundation Data Science Centre London UK Health Data Research UK London UK National Institute for Health Research Biomedical Research Centre at University College London Hospitals London UK Institute for Medical Engineering and Science Massachusetts Institute of Technology Massachusetts USA Pattern Recognition and Image Analysis Lab University of Münster Münster Germany

The COVID-19 pandemic exposed a global deficiency of systematic, data-driven guidance to identify high-risk individuals. Here, we illustrate the utility of routinely recorded medical history to predict the risk for 1741 diseases across clinical specialties and support the rapid response to emerging health threats such as COVID-19. We developed a neural network to learn from health records of 502,489 UK Biobank participants. Importantly, we observed discriminative improvements over basic demographic predictors for 1546 (88.8%) endpoints. After transferring the unmodified risk models to the All of US cohort, we replicated these improvements for 1115 (78.9%) of 1414 investigated endpoints, demonstrating generalizability across healthcare systems and historically underrepresented groups. Ultimately, we showed how this approach could have been used to identify individuals vulnerable to severe COVID-19. Our study demonstrates the potential of medical history to support guidance for emerging pandemics by systematically estimating risk for thousands of diseases at once at minimal cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RL Perceptron: Generalization Dynamics of Policy Learning in High Dimensions

引用

Physical Review X 2025年第2期15卷 021051-021051页

作者： Nishil Patel Sebastian Lee Stefano Sarao Mannelli Sebastian Goldt Andrew Saxe Gatsby Computational Neuroscience Unit University College London Gower Street London WC1E 6BT United Kingdom Imperial College London Exhibition Road South Kensington London SW7 2AZ United Kingdom Data Science and AI Computer Science and Engineering Chalmers University of Technology and University of Gothenburg Gothenburg Sweden School of Computer Science and Applied Mathematics University of the Witwatersrand Johannesburg South Africa International School of Advanced Studies (SISSA) Via Bonomea 265 34136 Trieste Italy Sainsbury Wellcome Centre University College London 25 Howland Street London W1T 4JG United Kingdom

Reinforcement learning (RL) algorithms have transformed many domains of machine learning. To tackle real-world problems, RL often relies on neural networks to learn policies directly from pixels or other high-dimensional sensory input. By contrast, many theories of RL have focused on discrete state spaces or worst-case analysis, and fundamental questions remain about the dynamics of policy learning in high-dimensional settings. Here, we propose a solvable high-dimensional RL model that can capture a variety of learning protocols, and we derive its typical policy learning dynamics as a set of closed-form ordinary differential equations. We obtain optimal schedules for the learning rates and task difficulty—analogous to annealing schemes and curricula during training in RL—and show that the model exhibits rich behavior, including delayed learning under sparse rewards, a variety of learning regimes depending on reward baselines, and a speed-accuracy trade-off driven by reward stringency. Experiments on variants of the Procgen game “Bossfight” and Arcade Learning Environment game “Pong” also show such a speed-accuracy trade-off in practice. Together, these results take a step toward closing the gap between theory and practice in high-dimensional RL.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Machine learning for modelling unstructured grid data in computational physics: A review

引用

Information Fusion 2025年 123卷

作者： Cheng, Sibo Bocquet, Marc Ding, Weiping Finn, Tobias Sebastian Fu, Rui Fu, Jinlong Guo, Yike Johnson, Eleda Li, Siyi Liu, Che Moro, Eric Newton Pan, Jie Piggott, Matthew Quilodran, Cesar Sharma, Prakhar Wang, Kun Xiao, Dunhui Xue, Xiao Zeng, Yong Zhang, Mingrui Zhou, Hao Zhu, Kewei Arcucci, Rossella CEREA ENPC EDF R&D Institut Polytechnique de Paris Île-de-France France School of Artificial Intelligence and Computer Science Nantong University Jiangsu Nantong226019 China School of Mathematical Sciences Key Laboratory of Intelligent Computing and Applications Tongji University Shanghai200092 China Faculty of Data Science City University of Macau 999078 China School of Engineering and Materials Science Faculty of Science and Engineering Queen Mary University of London LondonE1 4NS United Kingdom Zienkiewicz Centre for Modelling Data and AI Faculty of Science and Engineering Swansea University SwanseaSA1 8EN United Kingdom Department of Computer Science and Engineering Hong Kong university of science and technology Hong Kong Department of Earth Science & Engineering Imperial College London LondonSW7 2AZ United Kingdom Tianjin Key Laboratory of Imaging and Sensing Microelectronics Technology School of Microelectronics Tianjin University Tianjin300072 China T2N 1N4 Canada T2N 1N4 Canada Undaunted Grantham Institute for Climate Change and the Environment Imperial College London LondonSW7 2AZ United Kingdom Culham Campus AbingdonOX14 3DB United Kingdom Centre for Computational Science Department of Chemistry University College London LondonWC1H 0AJ United Kingdom H3G 1M8 Canada Australia Department of Chemical Engineering University College London LondonWC1E 6BT United Kingdom

Unstructured grid data are essential for modelling complex geometries and dynamics in computational physics. Yet, their inherent irregularity presents significant challenges for conventional machine learning (ML) techniques. This paper provides a comprehensive review of advanced ML methodologies designed to handle unstructured grid data in high-dimensional dynamical systems. Key approaches discussed include graph neural networks, transformer models with spatial attention mechanisms, interpolation-integrated ML methods, and meshless techniques such as physics-informed neural networks. These methodologies have proven effective across diverse fields, including fluid dynamics and environmental simulations. This review is intended as a guidebook for computational scientists seeking to apply ML approaches to unstructured grid data in their domains, as well as for ML researchers looking to address challenges in computational physics. It places special focus on how ML methods can overcome the inherent limitations of traditional numerical techniques and, conversely, how insights from computational physics can inform ML development. For this purpose, we mainly focus in this review on recent papers from the past decade that reflect strong interactions between computational physics and deep learning methods. To support benchmarking, this review also provides a summary of open-access datasets of unstructured grid data in computational physics. Finally, emerging directions such as generative models with unstructured data, reinforcement learning for mesh generation, and hybrid physics-data-driven paradigms are discussed to inspire future advancements in this evolving field. © 2025

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AA-ICP: Iterative closest point with anderson acceleration

AA-ICP: Iterative closest point with anderson acceleration

引用

2018 IEEE International Conference on Robotics and Automation, ICRA 2018

作者： Pavlov, Artem L. Ovchinnikov, Grigory W.V. Derbyshev, Dmitry Yu. Tsetserukou, Dzmitry Oseledets, Ivan V. Skolkovo Institute of Science and Technology Skolkovo Innovation Center Space Center Moscow143026 Russia Skolkovo Institute of Science and Technology Computational and Data-Intensive Science and Engineering Russia Moscow Institute of Physics and Technology Russia Skolkovo Institute of Science and Technology Space Center Russia Skolkovo Institute of Science and Technology Center for Computational and Data-Intensive Science and Engineering Russia

ISBN: (纸本)9781538630815

Iterative Closest Point (ICP) is a widely used method for performing scan-matching and registration. Being simple and robust, this method is still computationally expensive and may be challenging to use in real-time applications with limited resources on mobile platforms. In this paper we propose a novel effective method for acceleration of ICP which does not require substantial modifications to the existing code. This method is based on an idea of Anderson acceleration which is an iterative procedure for finding a fixed point of contractive mapping. The latter is often faster than a standard Picard iteration, usually used in ICP implementations. We show that ICP, being a fixed point problem, can be significantly accelerated by this method enhanced by heuristics to improve overall robustness. We implement proposed approach into Point Cloud Library (PCL) and make it available online. Benchmarking on the real-world data fully supports our claims. © 2018 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Logging Multi-Component Supply Chain Production in Blockchain 2021

Logging Multi-Component Supply Chain Production in Blockchai...

引用

4th International Conference on Computers in Management and Business, ICCMB 2021

作者： Madhwal, Yash Chistiakov, Ivan Yanovich, Yury Faculty of Computer Science National Research University Higher School of Economics Russia Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Russia Center for Computational and Data-Intensive Science and Engineering Skolkovo Inst. of Sci. and Technol. and Lab. of Data Mining and Predictive Modelling Inst. for Info. Transmiss. Prob. Russia

ISBN: (纸本)9781450388610

The supply chain is a thriving industry where numerous parties have different interests. Subsequently, the immense volume of data produced is difficult to audit. Some information can be lost or intentionally distorted in the process. Blockchain as an open, public, borderless, neutral, and censorship-resistant architecture can significantly complement supply chains. A new supply chain architecture is proposed in this work, where the tokenized directed acyclic hypergraph (DAG) represents real-world production processes. An anti-aerosol respirator manufacturing is used as an illustration example. By tokenizing all parts of multi-component products, supply chain data is automatically timestamped and secured. Moreover, the DAG design allows one to trace-back all the elements of the final product to their origin. Blockchain can formally audit the entire supply chain without the need to go from place to place. A single incorruptible operations log creates an enabling environment for an unbiased reputation system to emerge. © 2021 ACM.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Solution to Prevent Plastic Pipes Fraud* 7

Blockchain-Based Solution to Prevent Plastic Pipes Fraud*

引用

7th International Conference on Software Defined Systems, SDS 2020

作者： Kostyuk, Pavel Kudryashov, Sergey Madhwal, Yash Maslov, Ivan Tkachenko, Vladislav Yanovich, Yury Bitfury Russia Bitfury Moscow123112 Russia Center for Computational and Data-Intensive Science and Engineering Moscow121205 Russia Moscow119530 Russia

ISBN: (数字)9781728172194

ISBN: (纸本)9781728172194

Use of counterfeit plastic pipes has caused considerable financial damage to the states and companies. This article proposes a blockchain-based supply chain management system for its market. It can make pipes' use and life cycles transparent, thus guarantee the invariability of pipes mass produced and used. The article provides a high-level technical description, containing ERP-blockchain connection and application for project-specific labels printing, mobile applications for manufactures and pipes installers. © 2020 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

AccuRA: Accurate alignment of short reads on scalable reconfigurable accelerators 16

AccuRA: Accurate alignment of short reads on scalable reconf...

引用

16th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2016

作者： Natarajan, Santhi Kumar, N Krishna Pal, Debnath Nandy, S.K. Centre for Nano Science and Engineering Indian Institute of Science Bangalore India Department of Computational and Data Sciences Indian Institute of Science Bangalore India

ISBN: (纸本)9781509030767

Classified as a big data problem, Short Read Mapping (SRM) within the Next Generation Sequencing (NGS) pipeline presents profound technical and computing challenges. Existing solutions handle the high volume of data leveraging heuristics, to claim notable performance standards. The results from SRM leave a huge impact across fields, including medical diagnostics and drug discovery. In this context, we need precise, affordable, reliable and actionable results from SRM, to support any application, with uncompromised accuracy and performance. Here, we present AccuRA, a massively parallel, scalable, high performance reconfigurable accelerator for accurate alignment of short reads. Supplemented with multithreaded firmware architecture, AccuRA precisely aligns short reads, at a fine-grained single nucleotide resolution, and offers full coverage of the genome. AccuRA's parallel dynamic programming kernels seamlessly perform traceback process in hardware simultaneously along with forward scan, thus achieving SRM in the minimum possible and deterministic time. The AccuRA prototype, hosting eight kernel units on a single reconfigurable device, aligns short reads with an alignment performance of 20.48 Giga Cell Updates Per Second (GCUPs). AccuRA also scales well at multiple levels of design granularity, while successfully aligning genomes of various sizes, ranging from small archeal, bacterial, fungal genomes, to the large mammalian human genome. © 2016 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

New bounds and generalizations of locally recoverable codes with availability

New bounds and generalizations of locally recoverable codes ...

引用

作者： Kruglik, Stanislav Nazirkhanova, Kamilla Frolov, Alexey Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia Department of Radio Engineering and Cybernetics Moscow Institute of Physics and Technology Moscow141701 Russia

We investigate the distance properties of linear locally recoverable codes (LRC codes) with all-symbol locality and availability. New upper and lower bounds on the minimum distance of such codes are derived. The upper bound is based on the shortening method and generalized Hamming weights that are fundamental parameters of any linear codes with many useful applications. This bound improves existing upper bounds. To reduce the gap in between upper and lower bounds, we do not restrict the alphabet size and propose explicit constructions of codes with locality and availability via rank-metric codes. The first construction relies on expander graphs and is better in low rate region. The second construction utilizes the LRC codes developed by Wang et al. as inner codes and is better in high rate region. We also suggest one possible generalization of LRC codes in which the recovering sets can intersect in a small number of coordinates. This feature allows us to increase the achievable code rate and still meet load balancing requirements. We derive upper and lower bounds on the parameters of such codes and present explicit constructions of codes with such a property. © 1963-2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Estimation of the Second Moment Based on Rounded data

引用

Journal of Mathematical sciences (United States) 2019年第6期237卷 819-825页

作者： Samsonov, S.V. Ushakov, N.G. Ushakov, V.G. Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow Russian Federation Department of Mathematical Sciences Norwegian University of Science and Technology Trondheim Norway Moscow State University Moscow Russian Federation

Sample moments are unbiased estimators of theoretical moments (if the latter exist). In practice, however, observations are rounded under registration, which leads to systematic errors. In [1–3] it was shown that random measurement errors can provide the reduction of rounding errors, when the expectation is estimated by the first sample moment. This gives a possibility to manage the rounding error of the result, if one can add some noise to observations before registration. Moreover, this error can be made arbitrarily small. Now we find conditions under which this takes place for the second moment. © 2019, Springer science+Business Media, LLC, part of Springer Nature.

关键词： Estimators Registration second moment Noise Systematic errors Error measure Moment of force Rounding error Tea random measurement

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：