检索结果-内蒙古大学图书馆

33rd International Conference on Machine Learning, ICML 2016

作者： Patrini, Giorgio Nielsen, Frank Nock, Richard Carioni, Marcello Australian National University Australia Data61 Australia École Polytechnique France Sony Computer Science Laboratories Inc France Max Planck Institute for Mathematics in the Sciences Germany

ISBN: (纸本)9781510829008

We prove that the empirical risk of most wellknown loss functions factors into a linear term aggregating all labels with a term that is label free, and can further be expressed by sums of the same loss. This holds true even for non-smooth, non-convex losses and in any rkhs. The frrst term is a (kernel) mean operator - the focal quantity of this work - which we characterize as the sufficient statistic for the labels. The result tightens known generalization bounds and sheds new light on their interpretation. Factorization has a direct application on weakly supervised learning. In particular, we demonstrate that algorithms like sgd and proximal methods can be adapted with minimal effort to handle weak supervision, once the mean operator has been estimated. We apply this idea to learning with asymmetric noisy labels, connecting and extending prior work. Furthermore, we show that most losses enjoy a data-dependent (by the mean operator) form of noise robustness, in contrast with known negative results.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Exploring choice overload in related-article recommendations in digital libraries

arXiv

引用

arXiv 2017年

作者： Beierle, Felix Aizawa, Akiko Beel, Joeran Service-centric Networking Technische Universität Berlin Telekom Innovation Laboratories Berlin Germany Digital Content and Media Sciences Research Division Tokyo Japan Trinity College Dublin School of Computer Science and Statistics Intelligent Systems Discipline Knowledge and Data Engineering Group ADAPT Centre Dublin Ireland

We investigate the problem of choice overload – the difficulty of making a decision when faced with many options – when displaying related-article recommendations in digital libraries. So far, research regarding to how many items should be displayed has mostly been done in the fields of media recommendations and search engines. We analyze the number of recommendations in current digital libraries. When browsing fullscreen with a laptop or desktop PC, all display a fixed number of recommendations. 72% display three, four, or five recommendations, none display more than ten. We provide results from an empirical evaluation conducted with GESIS’ digital library Sowiport, with recommendations delivered by recommendations-as-a-service provider Mr. DLib. We use click-through rate as a measure of recommendation effectiveness based on 3.4 million delivered recommendations. Our results show lower click-through rates for higher numbers of recommendations and twice as many clicked recommendations when displaying ten instead of one related-articles. Our results indicate that users might quickly feel overloaded by choice. Copyright © 2017, The Authors. All rights reserved.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Genomic footprints of activated telomere maintenance mechanisms in cancer (Dec, 10.1038/s41467-019-13824-9, 2022)

引用

NATURE COMMUNICATIONS 2022年第1期13卷 1-1页

作者： Sieverling, Lina Hong, Chen Koser, Sandra D. Ginsbach, Philip Kleinheinz, Kortine Hutter, Barbara Braun, Delia M. Cortes-Ciriano, Isidro Xi, Ruibin Kabbe, Rolf Park, Peter J. Eils, Roland Schlesner, Matthias Brors, Benedikt Rippe, Karsten Jones, David T. W. Feuerbach, Lars Division of Applied Bioinformatics German Cancer Research Center (DKFZ) 69120 Heidelberg Germany Faculty of Biosciences Heidelberg University 69120 Heidelberg Germany Division of Applied Bioinformatics German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Biosciences Heidelberg University Heidelberg Germany Division of Theoretical Bioinformatics German Cancer Research Center (DKFZ) 69120 Heidelberg Germany Department for Bioinformatics and Functional Genomics Institute for Pharmacy and Molecular Biotechnology (IPMB) and BioQuant 69120 Heidelberg Germany Division of Theoretical Bioinformatics German Cancer Research Center (DKFZ) Heidelberg Germany Institute of Pharmacy and Molecular Biotechnology and BioQuant Heidelberg University Heidelberg Germany German Cancer Consortium (DKTK) Heidelberg Germany National Center for Tumor Diseases (NCT) Heidelberg Heidelberg Germany Heidelberg Center for Personalized Oncology (DKFZ-HIPO) German Cancer Research Center (DKFZ) Heidelberg Germany German Cancer Consortium (DKTK) German Cancer Research Center (DKFZ) Heidelberg Germany Division of Chromatin Networks German Cancer Research Center (DKFZ) and BioQuant 69120 Heidelberg Germany Department of Biomedical Informatics Harvard Medical School Boston Massachusetts 02115 USA Department of Chemistry Centre for Molecular Science Informatics University of Cambridge Cambridge CB2 1EW UK Ludwig Center at Harvard Medical School Boston Massachusetts 02115 USA Department of Biomedical Informatics Harvard Medical School Boston MA USA Department of Chemistry Centre for Molecular Science Informatics University of Cambridge Cambridge UK Ludwig Center at Harvard Medical School Boston MA USA School of Mathematical Sciences and Center for Statistical Science Peking University Beijing 100871 China Heidelberg University Heidelberg Germany New BIH Digital Health Center Berlin Institute of Health (BIH) and Charité - Universitätsmedizin Berlin Berlin Germany Bioi

来源：评论

学校读者我要写书评

暂无评论

Author Correction: A global biodiversity observing system to unite monitoring and guide action

引用

Nature ecology & evolution 2023年第12期7卷 2173页

作者： Andrew Gonzalez Petteri Vihervaara Patricia Balvanera Amanda E Bates Elisa Bayraktarov Peter J Bellingham Andreas Bruder Jillian Campbell Michael D Catchen Jeannine Cavender-Bares Jonathan Chase Nicholas Coops Mark J Costello Bálint Czúcz Aurélie Delavaud Maria Dornelas Grégoire Dubois Emmett J Duffy Hilde Eggermont Miguel Fernandez Nestor Fernandez Simon Ferrier Gary N Geller Michael Gill Dominique Gravel Carlos A Guerra Robert Guralnick Michael Harfoot Tim Hirsch Sean Hoban Alice C Hughes Wim Hugo Margaret E Hunter Forest Isbell Walter Jetz Norbert Juergens W Daniel Kissling Cornelia B Krug Peter Kullberg Yvan Le Bras Brian Leung Maria Cecilia Londoño-Murcia Jean-Michel Lord Michel Loreau Amy Luers Keping Ma Anna J MacDonald Joachim Maes Melodie McGeoch Jean Baptiste Mihoub Katie L Millette Zsolt Molnar Enrique Montes Akira S Mori Frank E Muller-Karger Hiroyuki Muraoka Masahiro Nakaoka Laetitia Navarro Tim Newbold Aidin Niamir David Obura Mary O'Connor Marc Paganini Dominique Pelletier Henrique Pereira Timothée Poisot Laura J Pollock Andy Purvis Adriana Radulovici Duccio Rocchini Claudia Roeoesli Michael Schaepman Gabriela Schaepman-Strub Dirk S Schmeller Ute Schmiedel Fabian D Schneider Mangal Man Shakya Andrew Skidmore Andrew L Skowno Yayioi Takeuchi Mao-Ning Tuanmu Eren Turak Woody Turner Mark C Urban Nicolás Urbina-Cardona Ruben Valbuena Anton Van de Putte Basile van Havre Vladimir Ruslan Wingate Elaine Wright Carlos Zambrana Torrelio Department of Biology Group on Earth Observations Biodiversity Observation Network McGill University Montreal Quebec Canada. andrew.gonzalez@mcgill.ca. Finnish Environment Institute Helsinki Finland. Instituto de Investigaciones en Ecosistemas y Sustentabilidad (IIES) Universidad Nacional Autónoma de México Morelia Mexico. Biology Department University of Victoria Victoria British Columbia Canada. EcoCommons Australia Research Specialised and Data Foundations Griffith University Nathan Queensland Australia. Manaaki Whenua - Landcare Research Lincoln New Zealand. Institute of Microbiology University of Applied Sciences and Arts of Southern Switzerland Mendrisio Switzerland. Secretariat of the Convention on Biological Diversity Montreal Quebec Canada. Department of Biology Group on Earth Observations Biodiversity Observation Network McGill University Montreal Quebec Canada. Department of Ecology Evolution and Behavior University of Minnesota Saint Paul MN USA. German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig Halle Germany. Department of Computer Sciences Martin Luther University Halle-Wittenberg Halle Germany. University of British Columbia Vancouver British Columbia Canada. Faculty of Biosciences and Aquaculture Nord Universitet Bodø Norway. Norwegian Institute for Nature Research (NINA) Trondheim Norway. Fondation for Research on Biodiversity (FRB) Paris France. Centre for Biological Diversity University of St Andrews St Andrews UK. Guia Marine Lab MARE Faculdade de Ciências da Universidade de Lisboa Cascais Portugal. Knowledge Centre for Biodiversity Joint Research Centre of the European Commission Ispra Italy. Tennenbaum Marine Observatories Network and MarineGEO program Smithsonian Environmental Research Center Edgewater MD USA. Belgian Science Policy Office Belgian Biodiversity Platform/Biodiversa+ Brussels Belgium. German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig Leipzig Germany.

来源：评论

学校读者我要写书评

暂无评论

Introducing evolutionary biologists to the analysis of big data: Guidelines to organize extended bioinformatics training courses

引用

Evolution: Education and Outreach 2018年第1期11卷 1-10页

作者： Faria, Rui Triant, Deborah Perdomo-Sabogal, Alvaro Overduin, Bert Bleidorn, Christoph Santana, Clara Isabel Bermudez Langenberger, David Indrischek, Henrike Aerts, Jan Engelhardt, Jan Engelken, Johannes Liebal, Katja Fasold, Mario Robb, Sofia Grath, Sonja Kolora, Sree Rohit Raj Carvalho, Tiago Salzburger, Walter Jovanovic, Vladimir Nowick, Katja CIBIO Centro de Investigação em Biodiversidade e Recursos Genéticos InBIO Laboratório Associado Universidade Do Porto Campus Agrário de Vairão Vairão 4485-661 Portugal IBE Institute of Evolutionary Biology (CSIC-UPF) Department of Experimental and Health Sciences Pompeu Fabra University Doctor Aiguader 88 Barcelona 08003 Spain Department of Animal and Plant Sciences University of Sheffield Sheffield United Kingdom Department of Biochemistry and Molecular Genetics University of Virginia Charlottesville 22908 VA United States TFome Research Group Bioinformatics Group Interdisciplinary Center of Bioinformatics Department of Computer Science University of Leipzig Härtelstrasse 16-18 Leipzig 04107 Germany Paul-Flechsig-Institute for Brain Research University of Leipzig Jahnallee 59 Leipzig 04109 Germany Faculty for Biology Chemistry and Pharmacy Freie Universität Berlin Königin-Luise-Straße 1-3 Berlin 14195 Germany Edinburgh Genomics University of Edinburgh Ashworth Laboratories King's Buildings Charlotte Auerbach Road Edinburgh EH9 3FL United Kingdom Museo Nacional de Ciencias Naturales Spanish Research Council (CSIC) José Gutiérrez Abascal 2 Madrid 28006 Spain German Centre for Integrative Biodiversity Research (IDiv) Halle-Jena-Leipzig Deutscher Platz 5e Leipzig 04103 Germany Grupo Rnomica Teórica y Computacional Departamento de Biologia Universidad Nacional de Colombia Bogota Colombia EcSeq Bioinformatics GmbH Sternwartenstraße 29 Leipzig 04103 Germany Computational Biology Department of Target Sciences GlaxoSmithKline Gunnels Wood Road Stevenage SG1 2NY United Kingdom Computational EvoDevo Group Department of Computer Science University of Leipzig Härtelstrasse 16-18 Leipzig 04107 Germany Bioinformatics Group Department of Computer Science University of Leipzig Härtelstrasse 16-18 Leipzig 04107 Germany Visual Data Analysis Lab ESAT/STADIUS KU Leuven Kasteelpark Arenberg 10 Leuven 3001 Belgium Imec KU Leuven Leuven Belgiu

Research in evolutionary biology has been progressively influenced by big data such as massive genome and transcriptome sequencing data, scalar measurements of several phenotypes on tens to thousands of individuals, as well as from collecting worldwide environmental data at an increasingly detailed scale. The handling and analysis of such data require computational skills that usually exceed the abilities of most traditionally trained evolutionary biologists. Here we discuss the advantages, challenges and considerations for organizing and running bioinformatics training courses of 2-3 weeks in length to introduce evolutionary biologists to the computational analysis of big data. Extended courses have the advantage of offering trainees the opportunity to learn a more comprehensive set of complementary topics and skills and allowing for more time to practice newly acquired competences. Many organizational aspects are common to any course, as the need to define precise learning objectives and the selection of appropriate and highly motivated instructors and trainees, among others. However, other features assume particular importance in extended bioinformatics training courses. To successfully implement a learning-by-doing philosophy, sufficient and enthusiastic teaching assistants (TAs) are necessary to offer prompt help to trainees. Further, a good balance between theoretical background and practice time needs to be provided and assured that the schedule includes enough flexibility for extra review sessions or further discussions if desired. A final project enables trainees to apply their newly learned skills to real data or case studies of their interest. To promote a friendly atmosphere throughout the course and to build a close-knit community after the course, allow time for some scientific discussions and social activities. In addition, to not exhaust trainees and TAs, some leisure time needs to be organized. Finally, all organization should be done while keeping

关键词： Active learning Bioinformatics Evolutionary biology Extended course Genomics High-throughput-sequencing Programming Sustainable course

来源：评论

学校读者我要写书评

暂无评论

Self-Grouping Multi-network Clustering

Self-Grouping Multi-network Clustering

引用

IEEE International Conference on data Mining (ICDM)

作者： Jingchao Ni Wei Cheng Wei Fan Xiang Zhang Department of Electrical Engineering and Computer Science Case Western Reserve University NEC Laboratories America Baidu Research Big Data Lab College of Information Sciences and Technology Pennsylvania State University

ISBN: (纸本)9781509054749

Joint clustering of multiple networks has been shown to be more accurate than performing clustering on individual networks separately. Many multi-view and multi-domain network clustering methods have been developed for joint multi-network clustering. These methods typically assume there is a common clustering structure shared by all networks, and different networks can provide complementary information on this underlying clustering structure. However, this assumption is too strict to hold in many emerging real-life applications, where multiple networks have diverse data distributions. More popularly, the networks in consideration belong to different underlying groups. Only networks in the same underlying group share similar clustering structures. Better clustering performance can be achieved by considering such groups differently. As a result, an ideal method should be able to automatically detect network groups so that networks in the same group share a common clustering structure. To address this problem, we propose a novel method, ComClus, to simultaneously group and cluster multiple networks. ComClus treats node clusters as features of networks and uses them to differentiate different network groups. Network grouping and clustering are coupled and mutually enhanced during the learning process. Extensive experimental evaluation on a variety of synthetic and real datasets demonstrates the effectiveness of our method.

关键词： Clustering methods Tensile stress Measurement Symmetric matrices Conferences data mining Electrical engineering

来源：评论

学校读者我要写书评

暂无评论

Author Correction: COVID-19 Disease Map, building a computational repository of SARS-CoV-2 virus-host interaction mechanisms

引用

Scientific data 2020年第1期7卷 247页

作者： Marek Ostaszewski Alexander Mazein Marc E Gillespie Inna Kuperstein Anna Niarakis Henning Hermjakob Alexander R Pico Egon L Willighagen Chris T Evelo Jan Hasenauer Falk Schreiber Andreas Dräger Emek Demir Olaf Wolkenhauer Laura I Furlong Emmanuel Barillot Joaquin Dopazo Aurelio Orta-Resendiz Francesco Messina Alfonso Valencia Akira Funahashi Hiroaki Kitano Charles Auffray Rudi Balling Reinhard Schneider Luxembourg Centre for Systems Biomedicine University of Luxembourg Belvaux Luxembourg. European Institute for Systems Biology and Medicine (EISBM) Vourles France. Ontario Institute for Cancer Research Toronto Canada. College of Pharmacy and Health Sciences St. John's University Queens NY USA. Institut Curie PSL Research University Mines Paris Tech Inserm Paris France. Department of Biology Univ. Évry University of Paris-Saclay Genopole 91025 Évry France. European Molecular Biology Laboratory European Bioinformatics Institute (EMBL-EBI) Hinxton UK. Institute of Data Science and Biotechnology Gladstone Institutes San Francisco United States. Department of Bioinformatics-BiGCaT NUTRIM Maastricht University Maastricht The Netherlands. Maastricht Centre for Systems Biology Maastricht University Maastricht The Netherlands. Helmholtz Zentrum München Institute of Computational Biology Neuherberg Germany. Center for Mathematics Technische Universität München Garching Germany. Faculty of Mathematics and Natural Sciences University of Bonn Bonn Germany. University of Konstanz Department of Computer and Information Science Konstanz Germany. Monash University Faculty of Information Technology Melbourne Australia. Computational Systems Biology of Infection and Antimicrobial-Resistant Pathogens Institute for Bioinformatics and Medical Informatics (IBMI) University of Tübingen 72076 Tübingen Germany. Department of Computer Science University of Tübingen 72076 Tübingen Germany. German Center for Infection Research (DZIF) partner site Tübingen Germany. Department of Molecular and Medical Genetics School of Medicine Oregon Health & Science University Portland USA. Department of Systems Biology & Bioinformatics University of Rostock Rostock Germany. Stellenbosch Institute of Advanced Study (STIAS) Wallenberg Research Centre at Stellenbosch University 7602 Stellenbosch South Africa. Research Programme on Biomedical informatics Hospital del Mar Medical Research

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Power Flow Control design of high penetration renewable sources for AC inverter based microgrids

Nonlinear Power Flow Control design of high penetration rene...

引用

International Symposium on Power Electronics, Electrical Drives, Automation and Motion, SPEEDAM

作者： David G. Wilson Rush D. Robinett Wayne W. Weaver Raymond H. Byrne Joseph Young Electrical Science & Experiments Department Sandia National Laboratories Albuquerque NM Mechanical Engineering-Engineering Mechanics Michigan Technological University Houghton MI Electrical and Computer Engineering Michigan Technological University Houghton MI Data Analysis & Exploitation Department Sandia National Laboratories Albuquerque NM OptimoJoe Albuquerque NM

ISBN: (纸本)9781509020683

This paper presents a control design methodology that begins to address high penetration of renewable energy sources into networked AC microgrid systems. To bring about high performing microgrid systems that contain large amounts of stochastic sources and loads is a major goal for the future of electric power systems. Alternative methods for controlling and analyzing AC microgrid systems will provide understanding into tradeoffs that can be made during the design phase. This paper utilizes a control design methodology, based on Hamiltonian Surface Shaping and Power Flow Control (HSSPFC) [1] that regulates renewable energy sources, loads and identifies energy storage requirements for an AC microgrid system. Both static and dynamic stability conditions are derived for the AC microgrid system. Numerical simulations are performed to demonstrate stability and performance. Two scenarios are considered; i) simple random stochastic renewable source and load AC Microgrid example and ii) a random variable pulse load application for Navy ship AC microgrid systems.

关键词： Microgrids Energy storage Inverters Switches Feedforward neural networks Heuristic algorithms Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Sparse approximations of directed information graphs

Sparse approximations of directed information graphs

引用

IEEE International Symposium on Information Theory

作者： Christopher J. Quinn Ali Pinar Jing Gao Lu Su School of Industrial Engineering Purdue University West Lafayette IN USA Data Sciences & Cyber Anal. Dept. Sandia National Laboratories Livermore CA USA Dept. of Computer Science and Engineering University at Buffalo Buffalo NY USA

ISBN: (纸本)9781509018079

Given a network of agents interacting over time, which few interactions best characterize the dynamics of the whole network? We propose an algorithm that finds the optimal sparse approximation of a network. The user controls the level of sparsity by specifying the total number of edges. The networks are represented using directed information graphs, a graphical model that depicts causal influences between agents in a network. Goodness of approximation is measured with Kullback-Leibler divergence. The algorithm finds the best approximation with no assumptions on the topology or the class of the joint distribution.

关键词： Approximation algorithms Heuristic algorithms Graphical models Network topology Information theory Topology Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Distributed flexible nonlinear tensor factorization 30

Distributed flexible nonlinear tensor factorization

引用

30th Annual Conference on Neural Information Processing Systems, NIPS 2016

作者： Zhe, Shandian Zhang, Kai Wang, Pengyuan Lee, Kuang-Chih Xu, Zenglin Qi, Yuan Gharamani, Zoubin Dept. Computer Science Purdue University United States NEC Laboratories America PrincetonNJ United States Dept. Marketing University of Georgia Athens United States Yahoo Research United States Big Data Res. Center School Comp. Sci. Eng. Univ. of Electr. Sci. and Tech. of China China Ant Financial Service Group Alibaba China University of Cambridge United Kingdom

Tensor factorization is a powerful tool to analyse multi-way data. Recently proposed nonlinear factorization methods, although capable of capturing complex relationships, are computationally quite expensive and may suffer a severe learning bias in case of extreme data sparsity. Therefore, we propose a distributed, flexible nonlinear tensor factorization model, which avoids the expensive computations and structural restrictions of the Kronecker-product in the existing TGP formulations, allowing an arbitrary subset of tensorial entries to be selected for training. Meanwhile, we derive a tractable and tight variational evidence lower bound (ELBO) that enables highly decoupled, parallel computations and high-quality inference. Based on the new bound, we develop a distributed, key-value-free inference algorithm in the MAPREDUCE framework, which can fully exploit the memory cache mechanism in fast MAPREDUCE systems such as SPARK. Experiments demonstrate the advantages of our method over several state-of-the-art approaches, in terms of both predictive performance and computational efficiency. © 2016 NIPS Foundation - All Rights Reserved.

关键词： Computational efficiency

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：