检索结果-内蒙古大学图书馆

Cataloging the visible universe through bayesian inference at petascale

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Regier, Jeffrey Pamnany, Kiran Fischer, Keno Noack, Andreas Lam, Maximilian Revels, Jarrett Howard, Steve Giordano, Ryan Schlegel, David McAuliffe, Jon Thomas, Rollin Prabhat Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Parallel Computing Lab Intel Corporation Julia Computing Computer Science and AI Laboratories Massachusetts Institute of Technology Department of Statistics University of California Berkeley United States Lawrence Berkeley National Laboratory

Astronomical catalogs derived from wide-field imaging surveys are an important tool for understanding the Universe. We construct an astronomical catalog from 55 TB of imaging data using Celeste, a Bayesian variational inference code written entirely in the high-productivity programming language Julia. Using over 1.3 million threads on 650,000 Intel Xeon Phi cores of the Cori Phase II supercomputer, Celeste achieves a peak rate of 1.54 DP PFLOP/s. Celeste is able to jointly optimize parameters for 188M stars and galaxies, loading and processing 178 TB across 8192 nodes in 14.6 minutes. To achieve this, Celeste exploits parallelism at multiple levels (cluster, node, and thread) and accelerates I/O through Cori’s Burst Buffer. Julia’s native performance enables Celeste to employ high-level constructs without resorting to handwritten or generated low-level code (C/C++/Fortran), and yet achieve petascale *** Codes 85A35, 68W10, 62P35 Copyright © 2018, The Authors. All rights reserved.

关键词： Inference engines

Federated Learning Enables Big Data for Rare Cancer Boundary Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pati, Sarthak Baid, Ujjwal Edwards, Brandon Sheller, Micah Wang, Shih-Han Reina, G. Anthony Foley, Patrick Gruzdev, Alexey Karkada, Deepthi Davatzikos, Christos Sako, Chiharu Ghodasara, Satyam Bilello, Michel Mohan, Suyash Vollmuth, Philipp Brugnara, Gianluca Preetha, Chandrakanth J. Sahm, Felix Maier-Hein, Klaus Zenk, Maximilian Bendszus, Martin Wick, Wolfgang Calabrese, Evan Rudie, Jeffrey Villanueva-Meyer, Javier Cha, Soonmee Ingalhalikar, Madhura Jadhav, Manali Pandey, Umang Saini, Jitender Garrett, John Larson, Matthew Jeraj, Robert Currie, Stuart Frood, Russell Fatania, Kavi Huang, Raymond Y. Chang, Ken Balana, Carmen Capellades, Jaume Puig, Josep Trenkler, Johannes Pichler, Josef Necker, Georg Haunschmidt, Andreas Meckel, Stephan Shukla, Gaurav Liem, Spencer Alexander, Gregory S. Lombardo, Joseph Palmer, Joshua D. Flanders, Adam E. Dicker, Adam P. Sair, Haris I. Jones, Craig K. Venkataraman, Archana Jiang, Meirui So, Tiffany Y. Chen, Cheng Heng, Pheng Ann Dou, Qi Kozubek, Michal Lux, Filip Michálek, Jan Matula, Petr Keřkovský, Miloš Kopřivová, Tereza Dostál, Marek Vybíhal, Václav Vogelbaum, Michael A. Mitchell, J. Ross Farinhas, Joaquim Maldjian, Joseph A. Yogananda, Chandan Ganesh Bangalore Pinho, Marco C. Reddy, Divya Holcomb, James Wagner, Benjamin C. Ellingson, Benjamin M. Cloughesy, Timothy F. Raymond, Catalina Oughourlian, Talia Hagiwara, Akifumi Wang, Chencai To, Minh-Son Bhardwaj, Sargam Chong, Chee Agzarian, Marc Falcão, Alexandre Xavier Martins, Samuel B. Teixeira, Bernardo C.A. Sprenger, Flávia Menotti, David Lucio, Diego R. LaMontagne, Pamela Marcus, Daniel Wiestler, Benedikt Kofler, Florian Ezhov, Ivan Metz, Marie Jain, Rajan Lee, Matthew Lui, Yvonne W. McKinley, Richard Slotboom, Johannes Radojewski, Piotr Meier, Raphael Wiest, Roland Derrick, Murcia Fu, Eric Haas, Rourke Thompson, John Ormond, David Ryan Badve, Chaitra Sloan, Andrew E. Vadmal, Vachan Waite, Kristin Colen, Rivka R. Pei, Linmin Ak, Murat Srinivasan, Ashok Bapuraj, J. Rajiv Rao, Arvind Wang, Nicholas Yoshiaki, Ota Moritani, Tos University of Pennsylvania PhiladelphiaPA United States Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Informatics Technical University of Munich Bavaria Munich Germany Intel Corporation Santa ClaraCA United States Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Heidelberg Germany Department of Neuropathology Heidelberg University Hospital Heidelberg Germany Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Neurology Clinic Heidelberg University Hospital Heidelberg Germany Department of Radiology & Biomedical Imaging University of California San Francisco San FranciscoCA United States Symbiosis Center for Medical Image Analysis Symbiosis International University Maharashtra Pune India Department of Neuroimaging and Interventional Radiology National Institute of Mental Health and Neurosciences Karnataka Bangalore India Department of Radiology School of Medicine and Public Health University of Wisconsin MadisonWI United States Department of Medical Physics School of Medicine and Public Health University of Wisconsin MadisonWI United States Department of Neuroradiology Clinical Neuroscience Center University Hospital Zurich University of Zurich Zurich Switzerland Leeds Teaching Hospitals Trust Department of Radiology Leeds United Kingdom Department of Radiology Brigham and Women's Hospital Harvard Medical School BostonMA United States Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Catalan Institute of Oncology Badalona Spain Consorci MAR Parc de Salut de Barcelona Catalonia Spain Josep Trueta University Hospital Girona Spain

Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally sharing ample, and importantly diverse, data from multiple sites. However, such centralization is challenging to scale (or even not feasible) due to various limitations. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here we present findings from the largest FL study to-date, involving data from 71 healthcare institutions across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, utilizing the largest dataset of such patients ever used in the literature (25,256 MRI scans from 6,314 patients). We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent. We anticipate our study to: 1) enable more studies in healthcare informed by large and diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further quantitative analyses for glioblastoma via performance optimization of our consensus model for eventual public release, and 3) demonstrate the effectiveness of FL at such scale and task complexity as a paradigm shift for multi-site collaborations, alleviating the need for data sharing. © 2022, CC BY.

关键词： Tumors

Joint learning of discriminative low-dimensional image representations based on dictionary learning and two-layer orthogonal projections

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wei, Xian Shen, Hao Li, Yuanxiang Tang, Xuan Jin, Bo Zhao, Lijun Murphey, Yi Lu Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences China Technical University of Munich Germany and fortiss GmbH Munich Germany Shanghai Key Lab for Trustworthy Computing School of Computer Science and Software Engineering East China Normal University China School of Aeronautics & Astronautics Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China Department of Electrical and Computer Engineering University of Michigan-Dearborn DearbornMI48128 United States

This work investigates the problem of efficiently learning discriminative low-dimensional representations of multi-class large-scale image objects. We propose a generic deep learning approach by taking advantages of Convolutional Neural Networks (CNN), sparse dictionary learning, and orthogonal projections. CNN is not only powerful on feature extraction, but also robust to spatial variance and changes. Sparse dictionary learning is well known for disentangling nonlinear underlying discriminative factors in data. The orthogonal projection is a notable efficient tool to project multi-class data onto low dimensional discriminative subspace. The proposed procedure can be summarized as follows. At first, a CNN is employed to extract high-dimensional (HD) preliminary convolutional features. Secondly, to avoid the high computational cost of direct sparse coding on HD CNN features, we present to learn sparse representation (SR) in an orthogonal projected space over a task-driven sparsifying dictionary. We then exploit the discriminative projection on SR. The whole learning process is treated as a joint optimization problem of trace quotient maximization, which involves the CNN parameters, the orthogonal projection on CNN features, the dictionary and the discriminative projection on sparse codes. The related cost function is well defined on product manifold of the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. It is optimized via a geometrical stochastic gradient descent algorithm. Finally, the quality of dictionary and projections learned by the proposed approach is further investigated in terms of image classification. The experimental results show that the approach can achieve a strongly competitive performance with state-of-the-art image classification methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

Eavesdropper's ability to attack a free-space quantum-key-distribution receiver in atmospheric turbulence

学校读者我要写书评

暂无评论

Physical Review A 2019年第6期99卷 062315-062315页

作者： Poompong Chaiwongkhot Katanya B. Kuntz Yanbao Zhang Anqi Huang Jean-Philippe Bourgoin Shihan Sajeed Norbert Lütkenhaus Thomas Jennewein Vadim Makarov Institute for Quantum Computing University of Waterloo Waterloo ON Canada N2L 3G1 Department of Physics and Astronomy University of Waterloo Waterloo ON Canada N2L 3G1 NTT Basic Research Laboratories NTT Corporation Atsugi Kanagawa 243-0198 Japan NTT Research Center for Theoretical Quantum Physics NTT Corporation Atsugi Kanagawa 243-0198 Japan Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha 410073 People's Republic of China Department of Electrical and Computer Engineering University of Waterloo Waterloo ON Canada N2L 3G1 Aegis Quantum Waterloo ON Canada Department of Electrical and Computer Engineering University of Toronto Toronto Canada M5S 3G4 Quantum Information Science Program Canadian Institute for Advanced Research Toronto ON Canada M5G 1Z8 Russian Quantum Center Skolkovo Moscow 143025 Russia Shanghai Branch National Laboratory for Physical Sciences at Microscale and CAS Center for Excellence in Quantum Information University of Science and Technology of China Shanghai 201315 People's Republic of China NTI Center for Quantum Communications National University of Science and Technology MISiS Moscow 119049 Russia

The ability of an eavesdropper (Eve) to perform an intercept-resend attack on a free-space quantum-key-distribution (QKD) receiver by precisely controlling the incidence angle of an attack laser has been previously demonstrated. However, such an attack could be ineffective in the presence of atmospheric turbulence due to beam wander and spatial mode aberrations induced by the air's varying index of refraction. We experimentally investigate the impact turbulence has on Eve's attack on a free-space polarization-encoding QKD receiver by emulating atmospheric turbulence with a spatial light modulator. Our results identify how well Eve would need to compensate for turbulence to perform a successful attack by either reducing her distance to the receiver or using beam wavefront correction via adaptive optics. Furthermore, we use an entanglement-breaking scheme to find a theoretical limit on the turbulence strength that hinders Eve's attack.

关键词： Quantum cryptography

The evolutionary history of 2,658 cancers (vol 578, pg 122, 2020)

学校读者我要写书评

暂无评论

NATURE 2023年第7948期614卷 E42-E42页

作者： Gerstung, Moritz Jolly, Clemency Leshchiner, Ignaty Dentro, Stefan C. Gonzalez, Santiago Rosebrock, Daniel Mitchell, Thomas J. Rubanova, Yulia Anur, Pavana Yu, Kaixian Tarabichi, Maxime Deshwar, Amit Wintersinger, Jeff Kleinheinz, Kortine Vazquez-Garcia, Ignacio Haase, Kerstin Jerman, Lara Sengupta, Subhajit Macintyre, Geoff Malikic, Salem Donmez, Nilgun Livitz, Dimitri G. Cmero, Marek Demeulemeester, Jonas Schumacher, Steven Fan, Yu Yao, Xiaotong Lee, Juhee Schlesner, Matthias Boutros, Paul C. Bowtell, David D. Zhu, Hongtu Getz, Gad Imielinski, Marcin Beroukhim, Rameen Sahinalp, S. Cenk Ji, Yuan Peifer, Martin Markowetz, Florian Mustonen, Ville Yuan, Ke Wang, Wenyi Morris, Quaid D. Spellman, Paul T. Wedge, David C. Van Loo, Peter European Molecular Biology Laboratory European Bioinformatics Institute (EMBL-EBI) Cambridge UK European Molecular Biology Laboratory Genome Biology Unit Heidelberg Germany Wellcome Sanger Institute Cambridge UK Genome Biology Unit European Molecular Biology Laboratory (EMBL) Heidelberg Germany University of Ljubljana Ljubljana Slovenia The Francis Crick Institute London UK Big Data Institute University of Oxford Oxford UK Wellcome Sanger Institute Wellcome Genome Campus Hinxton UK Big Data Institute Li Ka Shing Centre University of Oxford Oxford UK University of Cambridge Cambridge UK Cambridge University Hospitals NHS Foundation Trust Cambridge UK Department of Applied Mathematics and Theoretical Physics Centre for Mathematical Sciences University of Cambridge Cambridge UK Department of Epidemiology and Biostatistics Memorial Sloan Kettering Cancer Center New York NY USA Department of Statistics Columbia University New York NY USA Department of Haematology University of Cambridge Cambridge UK University of Leuven Leuven Belgium Broad Institute of MIT and Harvard Cambridge MA USA Center for Cancer Research Massachusetts General Hospital Charlestown MA USA Department of Pathology Massachusetts General Hospital Boston MA USA Harvard Medical School Boston MA USA Center for Cancer Research Massachusetts General Hospital Boston MA USA Dana-Farber Cancer Institute Boston MA USA Department of Medical Oncology Dana-Farber Cancer Institute Boston MA USA Department of Cancer Biology Dana-Farber Cancer Institute Boston MA USA Oxford NIHR Biomedical Research Centre Oxford UK Oxford NIHR Biomedical Research Centre University of Oxford Oxford UK University of Toronto Toronto Ontario Canada Vector Institute Toronto Ontario Canada Vector Institute Toronto ON Canada Department of Computer Science University of Toronto Toronto ON Canada Ontario Institute for Cancer Research Toronto Ontario Canada University of California Los Angeles

Combined effects of hydrometeorological hazards and urbanisation on dengue risk in Brazil: a spatiotemporal modelling study

学校读者我要写书评

暂无评论

The Lancet Planetary Health 2021年第4期5卷 e209-e219页

作者： Lowe, Rachel Lee, Sophie A Brady, Oliver J Bastos, Leonardo Carrasco-Escobar, Gabriel de Castro Catão, Rafael Colón-González, Felipe J Barcellos, Christovam Carvalho, Marilia Sá Blangiardo, Marta Rue, Håvard Gasparrini, Antonio Centre for Mathematical Modelling of Infectious Diseases London School of Hygiene & Tropical Medicine London United Kingdom Centre on Climate Change and Planetary Health London School of Hygiene & Tropical Medicine London United Kingdom Department of Infectious Disease Epidemiology London School of Hygiene & Tropical Medicine London United Kingdom Department of Public Health Environments and Society London School of Hygiene & Tropical Medicine London United Kingdom Centre for Statistical Modelling London School of Hygiene & Tropical Medicine London United Kingdom Scientific Computing Program Oswaldo Cruz Foundation Rio de Janeiro Brazil Health Information and Communication Institute Oswaldo Cruz Foundation Rio de Janeiro Brazil Scripps Institution of Oceanography University of California San Diego San Diego CA United States Health Innovation Laboratory Institute of Tropical Medicine Alexander von Humboldt Universidad Peruana Cayetano Heredia Lima Peru Department of Geography Federal University of Espírito Santo Vitória Brazil MRC Centre for Environment and Health Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia

Background: Temperature and rainfall patterns are known to influence seasonal patterns of dengue transmission. However, the effect of severe drought and extremely wet conditions on the timing and intensity of dengue epidemics is poorly understood. In this study, we aimed to quantify the non-linear and delayed effects of extreme hydrometeorological hazards on dengue risk by level of urbanisation in Brazil using a spatiotemporal model. Methods: We combined distributed lag non-linear models with a spatiotemporal Bayesian hierarchical model framework to determine the exposure-lag-response association between the relative risk (RR) of dengue and a drought severity index. We fit the model to monthly dengue case data for the 558 microregions of Brazil between January, 2001, and January, 2019, accounting for unobserved confounding factors, spatial autocorrelation, seasonality, and interannual variability. We assessed the variation in RR by level of urbanisation through an interaction between the drought severity index and urbanisation. We also assessed the effect of hydrometeorological hazards on dengue risk in areas with a high frequency of water supply shortages. Findings: The dataset included 12 895 293 dengue cases reported between 2001 and 2019 in Brazil. Overall, the risk of dengue increased between 0–3 months after extremely wet conditions (maximum RR at 1 month lag 1·56 [95% CI 1·41–1·73]) and 3–5 months after drought conditions (maximum RR at 4 months lag 1·43 [1·22–1·67]). Including a linear interaction between the drought severity index and level of urbanisation improved the model fit and showed the risk of dengue was higher in more rural areas than highly urbanised areas during extremely wet conditions (maximum RR 1·77 [1·32–2·37] at 0 months lag vs maximum RR 1·58 [1·39–1·81] at 2 months lag), but higher in highly urbanised areas than rural areas after extreme drought (maximum RR 1·60 [1·33–1·92] vs 1·15 [1·08–1·22], both at 4 months lag). We also found the den

关键词：

Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets

学校读者我要写书评

暂无评论

Nature methods 2024年第10期21卷 1959页

作者： Linus Manubens-Gil Zhi Zhou Hanbo Chen Arvind Ramanathan Xiaoxiao Liu Yufeng Liu Alessandro Bria Todd Gillette Zongcai Ruan Jian Yang Miroslav Radojević Ting Zhao Li Cheng Lei Qu Siqi Liu Kristofer E Bouchard Lin Gu Weidong Cai Shuiwang Ji Badrinath Roysam Ching-Wei Wang Hongchuan Yu Amos Sironi Daniel Maxim Iascone Jie Zhou Erhan Bas Eduardo Conde-Sousa Paulo Aguiar Xiang Li Yujie Li Sumit Nanda Yuan Wang Leila Muresan Pascal Fua Bing Ye Hai-Yan He Jochen F Staiger Manuel Peter Daniel N Cox Michel Simonneau Marcel Oberlaender Gregory Jefferis Kei Ito Paloma Gonzalez-Bellido Jinhyun Kim Edwin Rubel Hollis T Cline Hongkui Zeng Aljoscha Nern Ann-Shyn Chiang Jianhua Yao Jane Roskams Rick Livesey Janine Stevens Tianming Liu Chinh Dang Yike Guo Ning Zhong Georgia Tourassi Sean Hill Michael Hawrylycz Christof Koch Erik Meijering Giorgio A Ascoli Hanchuan Peng Institute for Brain and Intelligence Southeast University Nanjing China. Microsoft Corporation Redmond WA USA. Tencent AI Lab Bellevue WA USA. Computing Environment and Life Sciences Directorate Argonne National Laboratory Lemont IL USA. Kaya Medical Seattle WA USA. University of Cassino and Southern Lazio Cassino Italy. Center for Neural Informatics Structures and Plasticity Krasnow Institute for Advanced Study George Mason University Fairfax VA USA. Faculty of Information Technology Beijing University of Technology Beijing China. Beijing International Collaboration Base on Brain Informatics and Wisdom Services Beijing China. Nuctech Netherlands Rotterdam the Netherlands. Janelia Research Campus Howard Hughes Medical Institute Ashburn VA USA. Department of Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada. Ministry of Education Key Laboratory of Intelligent Computation and Signal Processing Anhui University Hefei China. Paige AI New York NY USA. Scientific Data Division and Biological Systems and Engineering Division Lawrence Berkeley National Lab Berkeley CA USA. Helen Wills Neuroscience Institute and Redwood Center for Theoretical Neuroscience UC Berkeley Berkeley CA USA. RIKEN AIP Tokyo Japan. Research Center for Advanced Science and Technology (RCAST) The University of Tokyo Tokyo Japan. School of Computer Science University of Sydney Sydney New South Wales Australia. Texas A&M University College Station TX USA. Cullen College of Engineering University of Houston Houston TX USA. Graduate Institute of Biomedical Engineering National Taiwan University of Science and Technology Taipei Taiwan. National Centre for Computer Animation Bournemouth University Poole UK. PROPHESEE Paris France. Department of Neuroscience Columbia University New York NY USA. Mortimer B. Zuckerman Mind Brain Behavior Institute Columbia University New York NY USA. Department of Computer Science Northern Illinois Universit

Quantum-statistical transport phenomena in memristive computing architectures

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Singh, Christopher N. Crafton, Brian A. West, Mathew P. Weidenbach, Alex S. Butler, Keith T. MacDonald, Allan H. Raychowdury, Arjit Vogel, Eric M. Alan Doolittle, W. Piper, L.F.J. Lee, Wei-Cheng Department of Physics Applied Physics and Astronomy Binghamton University BinghamtonNY13902 United States Materials Science and Technology Division Los Alamos National Laboratory Los AlamosNM87545 United States Department of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States SciML Scientific Computing Department Rutherford Appleton Laboratory DidcotOX110QX United Kingdom Department of Physics University of Texas at Austin AustinTX78712-1081 United States WMG University of Warwick CoventryCV4 7AL United Kingdom

The advent of reliable, nanoscale memristive components is promising for next generation compute-in-memory paradigms, however, the intrinsic variability in these devices has prevented widespread adoption. Here we show coherent electron wave functions play a pivotal role in the nanoscale transport properties of these emerging, non-volatile memories. By characterizing both filamentary and non-filamentary memristive devices as disordered Anderson systems, the switching characteristics and intrinsic variability arise directly from the universality of electron transport in disordered media. Our framework suggests localization phenomena in nanoscale, solid-state memristive systems are directly linked to circuit level performance. We discuss how quantum conductance fluctuations in the active layer set a lower bound on device variability. This finding implies there is a fundamental quantum limit on the reliability of memristive devices, and electron coherence will play a decisive role in surpassing or maintaining Moore’s Law with these systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Memristors

Deep learning on image denoising: An overview

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tian, Chunwei Fei, Lunke Zheng, Wenxian Xu, Yong Zuo, Wangmeng Lin, Chia-Wen Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen Guangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen Guangdong518055 China School of Computers Guangdong University of Technology Guangzhou Guangdong510006 China Tsinghua Shenzhen International Graduate School Shenzhen Guangdong518055 China Peng Cheng Laboratory Shenzhen Guangdong518055 China School of Computer Science and Technology Harbin Institute of Technology Harbin Heilongjiang150001 China Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan

Deep learning techniques have obtained much attention in image denoising. However, deep learning methods of different types deal with the noise have enormous differences. Specifically, discriminative learning based on deep learning can well address the Gaussian noise. Optimization model methods based on deep learning have good effect on estimating of the real noise. So far, there are little related researches to summarize different deep learning techniques for image denoising. In this paper, we make such a comparative study of different deep techniques in image denoising. We first classify the (1) deep convolutional neural networks (CNNs) for additive white noisy images, (2) deep CNNs for real noisy images, (3) deep CNNs for blind denoising and (4) deep CNNs for hybrid noisy images, which is the combination of noisy, blurred and low-resolution images. Then, we analyze the motivations and principles of deep learning methods of different types. Next, we compare and verify the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analysis. Finally, we point out some potential challenges and directions of future research. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks