检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Kazerooni, Anahita Fathi Khalili, Nastaran Liu, Xinyang Haldar, Debanjan Jiang, Zhifan Anwar, Syed Muhammed Albrecht, Jake Adewole, Maruf Anazodo, Udunna Anderson, Hannah Bagheri, Sina Baid, Ujjwal Bergquist, Timothy Borja, Austin J. Calabrese, Evan Chung, Verena Conte, Gian-Marco Dako, Farouk Eddy, James Ezhov, Ivan Familiar, Ariana Farahani, Keyvan Haldar, Shuvanjan Iglesias, Juan Eugenio Janas, Anastasia Johansen, Elaine Jones, Blaise V. Kofler, Florian LaBella, Dominic Lai, Hollie Anne Van Leemput, Koen Li, Hongwei Bran Maleki, Nazanin McAllister, Aaron S. Meier, Zeke Menze, Bjoern Moawad, Ahmed W. Nandolia, Khanak K. Pavaine, Julija Piraud, Marie Poussaint, Tina Prabhu, Sanjay P. Reitman, Zachary Rodriguez, Andres Rudie, Jeffrey D. Sanchez-Montano, Mariana Shaikh, Ibraheem Salman Shah, Lubdha M. Sheth, Nakul Shinohara, Russel Taki Tu, Wenxin Viswanathan, Karthik Wang, Chunhao Ware, Jeffrey B. Wiestler, Benedikt Wiggins, Walter Zapaishchykova, Anna Aboian, Mariam Bornhorst, Miriam de Blank, Peter Deutsch, Michelle Fouladi, Maryam Hoffman, Lindsey Kann, Benjamin Lazow, Margot Mikael, Leonie Nabavizadeh, Ali Packer, Roger Resnick, Adam Rood, Brian Vossough, Arastoo Bakas, Spyridon Linguraru, Marius George Children’s Hospital of Philadelphia PhiladelphiaPA United States Department of Neurosurgery University of Pennsylvania PhiladelphiaPA United States University of Pennsylvania PhiladelphiaPA United States Sheikh Zayed Institute for Pediatric Surgical Innovation Children’s National Hospital WashingtonDC United States Department of Neurosurgery Thomas Jefferson University Hospital PA United States Sage Bionetworks United States Lab Crestview Radiology Lagos Nigeria McGill University MontrealQC Canada Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Neurosurgery The University of Southern California CA United States Department of Radiology Duke University Medical Center United States Mayo Clinic MN United States Center for Global Health Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Informatics Technical University Munich Germany TranslaTUM - Central Institute for Translational Cancer Research Technical University of Munich Germany Cancer Imaging Program National Cancer Institute National Institutes of Health BethesdaMD United States Biomedical Engineering Rutgers University New BrunswickNJ United States Athinoula A Martinos Center for Biomedical Imaging Massachusetts General Hospital BostonMA United States Yale University New HavenCT United States PrecisionFDA U.S. Food and Drug Administration Silver SpringMD United States Cincinnati Children’s Hospital Medical Center United States Helmholtz AI Helmholtz Munich Germany Department of Radiation Oncology Duke University Medical Center United States Department of Radiology Children’s Health Orange County CA United States Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Radiol

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors. © 2023, CC BY.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Noisy Hegselmann-Krause systems: Phase transition and the 2R-conjecture 55

Noisy Hegselmann-Krause systems: Phase transition and the 2R...

引用

55th IEEE Conference on Decision and Control, CDC 2016

作者： Wang, Chu Li, Qianxiao Weinan, E. Chazelle, Bernard Program in Applied and Computational Mathematics Princeton University PrincetonNJ08540 United States Nokia Bell Labs 600 Mountain Avenue Murray HillNJ07974 United States Department of Mathematics Program in Applied and Computational Mathematics Princeton University NJ08540 United States Department of Computer Science Princeton University PrincetonNJ08540 United States

ISBN: (纸本)9781509018376

The classic Hegselmann-Krause (HK) model for opinion dynamics consists of a set of agents on the real line, each one instructed to move, at every time step, to the mass center of the agents within a fixed distance R. In this work, we investigate the effects of noise in the continuous-time version of the model as described by its mean-field Fokker-Planck equation. In the presence of a finite number of agents, the system exhibits a phase transition from order to disorder as the noise increases. We introduce an order parameter to track the phase transition and resolve the corresponding phase diagram. The system undergoes a phase transition for small R but none for larger R. Based on the stability analysis of the mean-field equation, we derive the existence of a forbidden zone for the disordered phase to emerge. We also provide a theoretical explanation for the well-known 2R conjecture, which states that, for a random initial distribution in a fixed interval, the final configuration consists of clusters separated by a distance of roughly 2R. Our theoretical analysis confirms previous simulations and predicts properties of the noisy HK model in higher dimension. © 2016 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Learning for Sequential Decision Making for Expensive Cost Functions with Stochastic Binary Feedbacks

arXiv

引用

arXiv 2017年

作者： Wang, Yingfei Wang, Chu Powell, Warren Department of Computer Science Princeton University PrincetonNJ08540 United States Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544 United States Department of Operations Research and Financial Engineering Princeton University PrincetonNJ08544 United States

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance. The learner takes an active role in selecting samples from the instance pool. The goal is to maximize the probability of success in either offline (training) or online (testing) phases. Our problem is motivated by real-world applications where observations are time consuming and/or expensive. We develop a knowledge gradient policy using an online Bayesian linear classifier to guide the experiment by maximizing the expected value of information of labeling each alternative. We provide a finite-time analysis of the estimated error and show that the maximum likelihood estimator based produced by the KG policy is consistent and asymptotically normal. We also show that the knowledge gradient policy is asymptotically optimal in an offline setting. This work further extends the knowledge gradient to the setting of contextual bandits. We report the results of a series of experiments that demonstrate its efficiency. Copyright © 2017, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Euclid: Early Release Observations – A preview of the Euclid era through a galaxy cluster magnifying lens

arXiv

引用

arXiv 2024年

作者： Atek, Hakim Gavazzi, R. Weaver, J.R. Diego, J.M. Schrabback, T. Hatch, N.A. Aghanim, N. Dole, H. Hartley, W.G. Taamoli, S. Congedo, G. Jimenez-Teja, Y. Cuillandre, J.-C. Bañados, E. Belladitta, S. Bowler, R.A.A. Franco, M. Jauzac, M. Mahler, G. Richard, J. Rocci, P.-F. Serjeant, S. Toft, S. Abriola, D. Bergamini, P. Biviano, A. Dimauro, P. Ezziati, M. Golden-Marx, J.B. Grillo, C. Hughes, A.C.N. Kang, Y. Kneib, J.-P. Lombardi, M. Mamon, G.A. McPartland, C.J.R. Meneghetti, M. Miyatake, H. Montes, M. Mortlock, D.J. Oesch, P.A. Okabe, N. Rosati, P. Taylor, A.N. Tarsitano, F. Weller, J. Kluge, M. Laureijs, R. Paltani, S. Saifollahi, T. Schirmer, M. Stone, C. Mora, A. Altieri, B. Amara, A. Andreon, S. Auricchio, N. Baldi, M. Balestra, A. Bardelli, S. Basset, A. Bender, R. Bodendorf, C. Bonino, D. Branchini, E. Brescia, M. Brinchmann, J. Camera, S. Candini, G.P. Capobianco, V. Carbone, C. Cardone, V.F. Carretero, J. Casas, S. Castander, F.J. Castellano, M. Cavuoti, S. Cimatti, A. Conselice, C.J. Conversi, L. Copin, Y. Corcione, L. Courbin, F. Courtois, H.M. Da Silva, A. Degaudenzi, H. Di Giorgio, A.M. Dinis, J. Douspis, M. Dubath, F. Dupac, X. Dusini, S. Ealet, A. Farina, M. Farrens, S. Ferriol, S. Fotopoulou, S. Frailis, M. Franceschi, E. Galeotta, S. Gillard, W. Gillis, B. Giocoli, C. Gómez-Alvarez, P. Grazian, A. Grupp, F. Guzzo, L. Hailey, M. Haugan, S.V.H. Hoar, J. Hoekstra, H. Holliman, M.S. Holmes, W. Hook, I. Hormuth, F. Hornstrup, A. Hudelot, P. Jahnke, K. Jhabvala, M. Keihänen, E. Kermiche, S. Kiessling, A. Kitching, T. Kohley, R. Kubik, B. Kuijken, K. Kümmel, M. Kunz, M. Kurki-Suonio, H. Lahav, O. Le Mignant, D. Ligori, S. Lilje, P.B. Lindholm, V. Lloro, I. Maino, D. Maiorano, E. Mansutti, O. Marggraf, O. Markovic, K. Martinet, N. Marulli, F. Massey, R. Maurogordato, S. McCracken, H.J. Mei, S. Mellier, Y. Merlin, E. Meylan, G. Moresco, M. Moscardini, L. Nakajima, R. Nichol, R.C. Institut d’Astrophysique de Paris UMR 7095 CNRS Sorbonne Université 98 bis boulevard Arago Paris75014 France Aix-Marseille Université CNRS CNES LAM Marseille France Department of Astronomy University of Massachusetts AmherstMA01003 United States Instituto de Física de Cantabria Edificio Juan Jordá Avenida de los Castros Santander39005 Spain Universität Innsbruck Institut für Astro- und Teilchenphysik Technikerstr. 25/8 Innsbruck6020 Austria School of Physics and Astronomy University of Nottingham University Park NottinghamNG7 2RD United Kingdom Université Paris-Saclay CNRS Institut d’astrophysique spatiale Orsay91405 France Department of Astronomy University of Geneva ch. d’Ecogia 16 Versoix1290 Switzerland Physics and Astronomy Department University of California 900 University Ave. RiversideCA92521 United States Institute for Astronomy University of Edinburgh Royal Observatory Blackford Hill EdinburghEH9 3HJ United Kingdom Instituto de Astrofísica de Andalucía CSIC Glorieta de la Astronomía Granada18080 Spain Observatorio Nacional Rua General Jose Cristino 77-Bairro Imperial de Sao Cristovao Rio de Janeiro20921-400 Brazil Université Paris-Saclay Université Paris Cité CEA CNRS AIM Gif-sur-Yvette91191 France Max-Planck-Institut für Astronomie Königstuhl 17 Heidelberg69117 Germany INAF-Osservatorio di Astrofisica e Scienza dello Spazio di Bologna Via Piero Gobetti 93/3 Bologna40129 Italy Jodrell Bank Centre for Astrophysics Department of Physics and Astronomy University of Manchester Oxford Road ManchesterM13 9PL United Kingdom The University of Texas at Austin AustinTX78712 United States Department of Physics Centre for Extragalactic Astronomy Durham University South Road DH1 3LE United Kingdom Department of Physics Institute for Computational Cosmology Durham University South Road DH1 3LE United Kingdom Astrophysics Research Centre University of KwaZulu-Natal Westville Campus Durban4041 South Africa School of

We present the first analysis of the Euclid Early Release Observations (ERO) program that targets fields around two lensing clusters, Abell 2390 and Abell 2764. We use VIS and NISP imaging to produce photometric catalogs for a total of ∼ 500 000 objects. The imaging data reach a 5 σ typical depth in the range 25.1–25.4 AB in the NISP bands, and 27.1–27.3 AB in the VIS band. Using the Lyman-break method in combination with photometric redshifts, we search for high-redshift galaxies. We identify 30 Lyman-break galaxy (LBG) candidates at z > 6 and 139 extremely red sources (ERSs), most likely at lower redshift. The deeper VIS imaging compared to NISP means we can routinely identify high-redshift Lyman breaks of the order of 3 magnitudes, which reduces contamination by brown dwarf stars and low-redshift galaxies. The difficulty of spatially resolving most of these sources in 0′′ . 3 pix−1 imaging makes the distinction between galaxies and quasars more challenging. Spectroscopic followup campaigns of such bright sources will help constrain both the bright end of the ultraviolet galaxy luminosity function and the quasar luminosity function at z > 6, and constrain the physical nature of these objects. Additionally, we have performed a combined strong lensing and weak lensing analysis of A2390, and demonstrate how Euclid will contribute to better constraining the virial mass of galaxy clusters. From these data, we also identify optical and near-infrared counterparts of known z > 0.6 clusters, which exhibit strong lensing features, establishing the ability of Euclid to characterize high-redshift clusters. Finally, we provide a glimpse of Euclid’s ability to map the intracluster light out to larger radii than current facilities, enabling a better understanding of the cluster assembly history and mapping of the dark matter distribution. This initial dataset illustrates the diverse spectrum of legacy science that will be enabled by the Euclid survey. © 2024, CC BY.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Lamé Parameter Estimation from Static Displacement Field Measurements in the Framework of Nonlinear Inverse Problems

arXiv

引用

arXiv 2017年

作者： Hubmer, Simon Sherina, Ekaterina Neubauer, Andreas Scherzer, Otmar Johannes Kepler University Linz Doctoral Program Computational Mathematics Altenbergerstraße 69 LinzA-4040 Austria Technical University of Denmark Department of Applied Mathematics and Computer Science Asmussens Allé Kongens Lyngby 2800 Denmark Johannes Kepler University Linz Industrial Mathematics Institute Altenbergerstraße 69 LinzA-4040 Austria University of Vienna Computational Science Center Oskar Morgenstern-Platz 1 Vienna1090 Austria Johann Radon Institute Linz Altenbergerstraße 69 LinzA-4040 Austria

We consider a problem of quantitative static elastography, the estimation of the Lamé parameters from internal displacement field data. This problem is formulated as a nonlinear operator equation. To solve this equation, we investigate the Landweber iteration both analytically and numerically. The main result of this paper is the verification of a nonlinearity condition in an infinite dimensional Hilbert space context. This condition guarantees convergence of iterative regularization methods. Furthermore, numerical examples for recovery of the Lamé parameters from displacement data simulating a static elastography experiment are *** Codes 65J22, 65J15, 74G75 Copyright © 2017, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

5th International Conference on Variable Neighborhood Search (ICVNS'17)

引用

Electronic Notes in Discrete mathematics 2018年 66卷 1-5页

作者： Vitor Nazário Coelho Haroldo Gambini Santos Igor Machado Coelho Puca Huachi Vaz Penna Thays A. Oliveira Marcone Jamilson Freitas Souza Angelo Sifaleras Institute of Computer Science Universidade Federal Fluminense Niterói Brazil Grupo da Causa Humana Ouro Preto Brazil Department of Computing Universidade Federal de Ouro Preto Ouro Preto Brazil Institute of Mathematics Statitics Universidade Estadual do Rio de Janeiro Rio de Janeiro Brazil Graduate Program of the Department of Engineering and Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain Department of Applied Informatics School of Information Sciences University of Macedonia 156 Egnatia Str. Thessaloniki 54636 Greece

This volume presents selected, peer-reviewed, short papers that were accepted for presentation in the 5th International Conference on Variable Neighborhood Search (ICVNS'17) which was held in Ouro Preto, Brazil, d... 详细信息

关键词： Metaheuristics Variable Neighborhood Search Discrete Optimization Nonlinear optimization

来源：评论

学校读者我要写书评

暂无评论

Inertial Hegselmann-Krause systems

Inertial Hegselmann-Krause systems

引用

American Control Conference (ACC)

作者： Bernard Chazelle Chu Wang Department of Computer Science Princeton University Program in Applied and Computational Mathematics Princeton University

ISBN: (纸本)9781467386838

We derive an energy bound for inertial Hegselmann-Krause (HK) systems, which we define as a variant of the classic HK model in which the agents can change their weights arbitrarily at each step. We use the bound to prove the convergence of HK systems with closed-minded agents, which settles a conjecture of long standing. This paper also introduces anchored HK systems and show their equivalence to the symmetric heterogeneous model.

关键词： Convergence Communication networks Kinetic theory Protocols Nickel Mobile communication Turning

来源：评论

学校读者我要写书评

暂无评论

Forecasting: theory and practice

arXiv

引用

arXiv 2020年

作者： Petropoulos, Fotios Apiletti, Daniele Assimakopoulos, Vassilios Babai, Mohamed Zied Barrow, Devon K. Taieb, Souhaib Ben Bergmeir, Christoph Bessa, Ricardo J. Bijak, Jakub Boylan, John E. Browell, Jethro Carnevale, Claudio Castle, Jennifer L. Cirillo, Pasquale Clements, Michael P. Cordeiro, Clara Oliveira, Fernando Luiz Cyrino de Baets, Shari Dokumentov, Alexander Ellison, Joanne Fiszeder, Piotr Franses, Philip Hans Frazier, David T. Gilliland, Michael Gönül, M. Sinan Goodwin, Paul Grossi, Luigi Grushka-Cockayne, Yael Guidolin, Mariangela Guidolin, Massimo Gunter, Ulrich Guo, Xiaojia Guseo, Renato Harvey, Nigel Hendry, David F. Hollyman, Ross Januschowski, Tim Jeon, Jooyoung Jose, Victor Richmond R. Kang, Yanfei Koehler, Anne B. Kolassa, Stephan Kourentzes, Nikolaos Leva, Sonia Li, Feng Litsiou, Konstantia Makridakis, Spyros Martin, Gael M. Martinez, Andrew B. Meeran, Sheik Modis, Theodore Nikolopoulos, Konstantinos Önkal, Dilek Paccagnini, Alessia Panagiotelis, Anastasios Panapakidis, Ioannis Pavía, Jose M. Pedio, Manuela Pedregal, Diego J. Pinson, Pierre Ramos, Patrícia Rapach, David E. Reade, J. James Rostami-Tabar, Bahman Rubaszek, Michal Sermpinis, Georgios Shang, Han Lin Spiliotis, Evangelos Syntetos, Aris A. Talagala, Priyanga Dilini Talagala, Thiyanga S. Tashman, Len Thomakos, Dimitrios Thorarinsdottir, Thordis Todini, Ezio Arenas, Juan Ramón Trapero Wang, Xiaoqian Winkler, Robert L. Yusupova, Alisa Ziel, Florian School of Management University of Bath United Kingdom Politecnico di Torino Turin Italy Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece Kedge Business School France Department of Management Birmingham Business School University of Birmingham United Kingdom Belgium Faculty of Information Technology Monash University Melbourne Australia INESC TEC – Institute for Systems and Computer Engineering Technology and Science Porto Portugal Department of Social Statistics and Demography University of Southampton United Kingdom Centre for Marketing Analytics and Forecasting Lancaster University Management School Lancaster University United Kingdom School of Mathematics and Statistics University of Glasgow United Kingdom Department of Mechanical and Industrial Engineering University of Brescia Italy Magdalen College University of Oxford United Kingdom ZHAW School of Management and Law Zurich University of Applied Sciences Switzerland ICMA Centre Henley Business School University of Reading United Kingdom Faculdade de Ciências e Tecnologia Universidade do Algarve Portugal CEAUL Faculdade de Ciências Universidade de Lisboa Portugal Brazil Department of Business Informatics and Operations Management Faculty of Economics and Business Administration Universiteit Gent Belgium Let’s Forecast Australia Faculty of Economic Sciences and Management Nicolaus Copernicus University in Torun Poland Econometric Institute Erasmus School of Economics Rotterdam Netherlands Department of Econometrics and Business Statistics Monash University Melbourne Australia SAS United States Newcastle Business School Northumbria University Newcastle upon Tyne United Kingdom Department of Statistical Sciences University of Padua Italy Darden School of Business University of Virginia United States Finance Department Bocconi University Baffi-CAREFIN Centre Milan Italy Department of Tourism and Service Management MODUL Un

Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds the future is both exciting and challenging, with individuals and organisations seeking to minimise risks and maximise utilities. The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges. This article provides a non-systematic review of the theory and the practice of forecasting. We provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organise, and evaluate forecasts. We then demonstrate how such theoretical concepts are applied in a variety of real-life contexts. We do not claim that this review is an exhaustive list of methods and applications. However, we wish that our encyclopedic presentation will offer a point of reference for the rich work that has been undertaken over the last decades, with some key insights for the future of forecasting theory and practice. Given its encyclopedic nature, the intended mode of reading is non-linear. We offer cross-references to allow the readers to navigate through the various topics. We complement the theoretical concepts and applications covered by large lists of free or open-source software implementations and publicly-available databases. © 2020, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Rare variant analyses in 51,256 type 2 diabetes cases and 370,487 controls reveal the pathogenicity spectrum of monogenic diabetes genes

引用

Nature genetics 2025年第4期57卷 1060页

作者： Alicia Huerta-Chagoya Philip Schroeder Ravi Mandla Jiang Li Lowri Morris Maheak Vora Ahmed Alkanaq Dorka Nagy Lukasz Szczerbinski Jesper G S Madsen Silvia Bonàs-Guarch Fanny Mollandin Joanne B Cole Bianca Porneala Kenneth Westerman Josephine H Li Toni I Pollin Jose C Florez Anna L Gloyn David J Carey Inês Cebola Uyenlinh L Mirshahi Alisa K Manning Aaron Leong Miriam Udler Josep M Mercader Programs in Metabolism and Medical & Population Genetics Broad Institute of Harvard and MIT Cambridge MA USA. Center for Genomic Medicine Massachusetts General Hospital Boston MA USA. Diabetes Unit Massachusetts General Hospital Boston MA USA. Graduate Program in Genomics and Computational Biology University of Pennsylvania Philadelphia PA USA. Department of Genomic Health Geisinger Danville PA USA. Section of Genetics and Genomics Department of Metabolism Digestion and Reproduction Imperial College London London UK. National Heart and Lung Institute Faculty of Medicine London UK. Department of Endocrinology Diabetology and Internal Medicine Medical University of Bialystok Bialystok Poland. Clinical Research Centre Medical University of Bialystok Bialystok Poland. Institute of Mathematics and Computer Science University of Southern Denmark Odense Denmark. The Novo Nordisk Foundation Center for Genomic Mechanisms of Disease Broad Institute of MIT and Harvard Cambridge MA USA. Department of Biochemistry and Molecular Biology University of Southern Denmark Odense Denmark. Centre for Genomic Regulation The Barcelona Institute of Science and Technology Barcelona Spain. Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas Madrid Spain. Department of Metabolism Digestion and Reproduction Imperial College London London UK. Department of Medicine Harvard Medical School Boston MA USA. Division of Endocrinology Boston Children's Hospital Boston MA USA. Department of Biomedical Informatics University of Colorado School of Medicine Aurora CO USA. Division of General Internal Medicine Massachusetts General Hospital Boston MA USA. Department of Medicine Massachusetts General Hospital Boston MA USA. University of Maryland School of Medicine Baltimore MD USA. Endocrine Division Massachusetts General Hospital Boston MA USA. Department of Pediatrics Division of Endocrinology Stanford School of Medicine Stanford

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural networks with low-rank regularization 4

Convolutional neural networks with low-rank regularization

引用

4th International Conference on Learning Representations, ICLR 2016

作者： Tai, Cheng Xiao, Tong Zhang, Yi Wang, Xiaogang Weinan, E. Program in Applied and Computational Mathematics Princeton University United States Department of Electronic Engineering Chinese University of Hong Kong Hong Kong Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank tensor decomposition for removing the redundancy in the convolution kernels. The algorithm finds the exact global optimizer of the decomposition and is more effective than iterative methods. Based on the decomposition, we further propose a new method for training low-rank constrained CNNs from scratch. Interestingly, while achieving a significant speedup, sometimes the low-rank constrained CNNs delivers significantly better performance than their non-constrained counterparts. On the CIFAR-10 dataset, the proposed low-rank NIN model achieves 91.31% accuracy (without data augmentation), which also improves upon state-of-the-art result. We evaluated the proposed method on CIFAR-10 and ILSVRC12 datasets for a variety of modern CNNs, including AlexNet, NIN, VGG and GoogleNet with success. For example, the forward time of VGG-16 is reduced by half while the performance is still comparable. Empirical success suggests that low-rank tensor decompositions can be a very useful tool for speeding up large CNNs. © ICLR 2016: San Juan, Puerto Rico. All Rights Reserved.

关键词： Iterative methods

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：