检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Pion-Tonachini, Luca Bouchard, Kristofer Martin, Hector Garcia Peisert, Sean Holtz, W. Bradley Aswani, Anil Dwivedi, Dipankar Wainwright, Haruko Pilania, Ghanshyam Nachman, Benjamin Marrone, Babetta L. Falco, Nicola Prabhat Arnold, Daniel Wolf-Yadlin, Alejandro Powers, Sarah Climer, Sharlee Jackson, Quinn Carlson, Ty Sohn, Michael Zwart, Petrus Kumar, Neeraj Justice, Amy Tomlin, Claire Jacobson, Daniel Micklem, Gos Gkoutos, Georgios V. Bickel, Peter J. Cazier, Jean-Baptiste Müller, Juliane Webb-Robertson, Bobbie-Jo Stevens, Rick Anderson, Mark Kreutz-Delgado, Ken Mahoney, Michael W. Brown, James B. Pattern Computer Inc. Friday HarborWA98250 United States Biosciences Area Lawrence Berkeley National Lab BerkeleyCA94803 United States Computational Research Division Lawrence Berkeley National Lab BerkeleyCA94720 United States Helen Wils Neuroscience Institute Redwood Center for Theoretical Neuroscience Uc Berkeley BerkeleyCA94720 United States Doe Agile BioFoundry Lawrence Berkeley National Laboratory BerkeleyCA94803 United States Joint BioEnergy Institute Lawrence Berkeley National Laboratory BerkeleyCA94803 United States Bcam Basque Center for Applied Mathematics Bilbao48009 Spain Computer Science University of California Davis DavisCA95616 United States Cenic La MiradaCA90638 United States Health Informatics University of California Davis School of Medicine SacramentoCA95817 United States Berkeley Institute for Data Science University of California Berkeley BerkeleyCA94720 United States Industrial Engineering and Operations Research University of California Berkeley BerkeleyCA94720 United States Environmental & Earth Sciences Area Lawrence Berkeley National Laboratory BerkeleyCA94803 United States Nuclear Engineering University of California Berkeley BerkeleyCA94720 United States Materials Science and Technology Division Los Alamos National Laboratory Los AlamosNM87545 United States Physics Division Lawrence Berkeley National Lab BerkeleyCA94720 United States Bioscience Division Los Alamos National Laboratory Los AlamosNM87545 United States Earth and Environmental Sciences Area Lawrence Berkeley National Lab BerkeleyCA94803 United States Energy Technologies Area Lawrence Berkeley National Lab BerkeleyCA94803 United States Computing and Computational Sciences Oak Ridge National Laboratory Oak RidgeTN37831 United States Industrial & Systems Engineering The University of Tennessee KnoxvilleTN37996 United States Department of Computer Science University of Missouri-Saint Louis St. LouisMO63121 United

We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery. The distinct goals of AI for industry versus the goals of AI for science create tension between identifying patterns in data versus discovering patterns in the world from data. If we address the fundamental challenges associated with "bridging the gap" between domain-driven scientific models and data-driven AI learning machines, then we expect that these AI models can transform hypothesis generation, scientific discovery, and the scientific process itself. © 2021, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

NL-Augmenter A Framework for Task-Sensitive Natural Language Augmentation

arXiv

引用

arXiv 2021年

作者： Dhole, Kaustubh D. Gangal, Varun Gehrmann, Sebastian Gupta, Aadesh Li, Zhenhao Mahamood, Saad Mahendiran, Abinaya Mille, Simon Shrivastava, Ashish Tan, Samson Wu, Tongshuang Sohl-Dickstein, Jascha Choi, Jinho D. Hovy, Eduard Dušek, Ondřej Ruder, Sebastian Anand, Sajant Aneja, Nagender Banjade, Rabin Barthe, Lisa Behnke, Hanna Berlot-Attwell, Ian Boyle, Connor Brun, Caroline Sobrevilla Cabezudo, Marco Antonio Cahyawijaya, Samuel Chapuis, Emile Che, Wanxiang Choudhary, Mukund Clauss, Christian Colombo, Pierre Cornell, Filip Dagan, Gautier Das, Mayukh Dixit, Tanay Dopierre, Thomas Dray, Paul-Alexis Dubey, Suchitra Ekeinhor, Tatiana Giovanni, Marco Di Goyal, Tanya Gupta, Rishabh Hamla, Louanes Han, Sang Harel-Canada, Fabrice Honoré, Antoine Jindal, Ishan Joniak, Przemyslaw K. Kleyko, Denis Kovatchev, Venelin Krishna, Kalpesh Kumar, Ashutosh Langer, Stefan Lee, Seungjae Ryan Levinson, Corey James Liang, Hualou Liang, Kaizhao Liu, Zhexiong Lukyanenko, Andrey Marivate, Vukosi de Melo, Gerard Meoni, Simon Meyer, Maxime Mir, Afnan Moosavi, Nafise Sadat Muennighoff, Niklas Hon Mun, Timothy Sum Murray, Kenton Namysl, Marcin Obedkova, Maria Oli, Priti Pasricha, Nivranshu Pfister, Jan Plant, Richard Prabhu, Vinay Pais, Vasile Qin, Libo Raji, Shahab Rajpoot, Pawan Kumar Raunak, Vikas Rinberg, Roy Roberts, Nicholas Rodriguez, Juan Diego Roux, Claude Vasconcellos, P.H.S. Sai, Ananya B. Schmidt, Robin M. Scialom, Thomas Sefara, Tshephisho Shamsi, Saqib N. Shen, Xudong Shi, Yiwen Shi, Haoyue Shvets, Anna Siegel, Nick Sileo, Damien Simon, Jamie Singh, Chandan Sitelew, Roman Soni, Priyank Sorensen, Taylor Soto, William Srivastava, Aman Aditya Srivatsa, K.V. Sun, Tony Mukund Varma, T. Tabassum, A. Tan, Fiona Anting Teehan, Ryan Tiwari, Mo Tolkiehn, Marie Wang, Athena Wang, Zijian Wang, Zijie J. Wang, Gloria Wei, Fuxuan Wilie, Bryan Winata, Genta Indra Wu, Xinyi Wydmanski, Witold Xie, Tianbao Yaseen, Usama Yee, Michael A. Zhang, Jing Zhang, Yue ACKO Agara Amelia R&D New York United States Applied Research Laboratories The University of Texas at Austin United States Bloomberg Brigham Young University United States Carnegie Mellon University United States Center for Data and Computing in Natural Sciences Universität Hamburg Germany Charles River Analytics Charles University Prague Czech Republic Columbia University United States Council for Scientific and Industrial Research DeepMind United Kingdom Department of Computer Science University of Pretoria South Africa Drexel University United States Eberhard Karls University of Tübingen Germany Edinburgh Napier University United Kingdom Emory University United States Fablab by Inetum in Paris France Fraunhofer IAIS Germany Georgia Tech United States Google Brain United States Google Research United States Harbin Institute of Technology China Hasso Plattner Institute University of Potsdam Germany Hong Kong University of Science and Technology Hong Kong IBM Research IIT Delhi India IIT Madras India Illinois Mathematics and Science Academy United States Imperial College London United Kingdom Independent Indian Institute of Science Bangalore India Institut Teknologi Bandung Indonesia Institute of Data Science National University of Singapore Singapore International Institute of Information Technology Hyderabad India Jagiellonian University Poland Jean Monnet University France Johns Hopkins United States KTH Royal Institute of Technology Sweden KU Leuven Belgium MTS AI France Microsoft RedmondWA United States Mphasis NEXT Labs National University of Ireland Galway Ireland National University of Science and Technology Pakistan National University of Singapore Singapore Naver Labs Europe France Peking University China Politecnico di Milano University of Bologna Italy Polytechnic Institute of Paris France Pompeu Fabra University Spain Pontifical Catholic University of Minas Gerais Brazil Princeton University United States Rakuten India India Research Institu

data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters (data splits according to specific features). We describe the framework and an initial set of 117 transformations and 23 filters for a variety of natural language tasks. We demonstrate the efficacy of NL-Augmenter by using several of its tranformations to analyze the robustness of popular natural language models. The infrastructure, datacards and robutstness analysis results are available publicly on the NL-Augmenter repository (https://***/GEM-benchmark/NL-Augmenter). © 2021, CC BY.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

The NANOGrav 15 yr data Set: Looking for Signs of Discreteness in the Gravitational-wave Background

引用

The Astrophysical Journal 2024年第1期978卷 31-31页

作者： Gabriella Agazie Akash Anumarlapudi Anne M. Archibald Zaven Arzoumanian Jeremy George Baier Paul T. Baker Bence Bécsy Laura Blecha Adam Brazier Paul R. Brook Lucas Brown Sarah Burke-Spolaor J. Andrew Casey-Clyde Maria Charisi Shami Chatterjee Tyler Cohen James M. Cordes Neil J. Cornish Fronefield Crawford H. Thankful Cromartie Kathryn Crowter Megan E. DeCesar Paul B. Demorest Heling Deng Timothy Dolch Elizabeth C. Ferrara William Fiore Emmanuel Fonseca Gabriel E. Freedman Nate Garver-Daniels Peter A. Gentile Joseph Glaser Deborah C. Good Kayhan Gültekin Jeffrey S. Hazboun Ross J. Jennings Aaron D. Johnson Megan L. Jones Andrew R. Kaiser David L. Kaplan Luke Zoltan Kelley Matthew Kerr Joey S. Key Nima Laal Michael T. Lam William G. Lamb Bjorn Larsen T. Joseph W. Lazio Natalia Lewandowska Tingting Liu Duncan R. Lorimer Jing Luo Ryan S. Lynch Chung-Pei Ma Dustin R. Madison Alexander McEwen James W. McKee Maura A. McLaughlin Natasha McMann Bradley W. Meyers Patrick M. Meyers Chiara M. F. Mingarelli Andrea Mitridate Priyamvada Natarajan Cherry Ng David J. Nice Stella Koch Ocker Ken D. Olum Timothy T. Pennucci Benetge B. P. Perera Nihan S. Pol Henri A. Radovan Scott M. Ransom Paul S. Ray Joseph D. Romano Jessie C. Runnoe Shashwat C. Sardesai Ann Schmiedekamp Carl Schmiedekamp Kai Schmitz Brent Shapiro-Albert Xavier Siemens Joseph Simon Magdalena S. Siwek Sophia V. Sosa Fiscella Ingrid H. Stairs Daniel R. Stinebring Kevin Stovall Abhimanyu Susobhanan Joseph K. Swiggum Stephen R. Taylor Jacob E. Turner Caner Unal Michele Vallisneri Sarah J. Vigeland Haley M. Wahl London Willson Caitlin A. Witt David Wright Olivia Young Center for Gravitation Cosmology and Astrophysics Department of Physics University of Wisconsin-milwaukee P.O. Box 413 Milwaukee WI 53201 USA Newcastle University NE1 7RU UK X-Ray Astrophysics Laboratory NASA Goddard Space Flight Center Code 662 Greenbelt MD 20771 USA Department of Physics Oregon State University Corvallis OR 97331 USA Department of Physics and Astronomy Widener University One University Place Chester PA 19013 USA Physics Department University of Florida Gainesville FL 32611 USA Cornell Center for Astrophysics and Planetary Science and Department of Astronomy Cornell University Ithaca NY 14853 USA Cornell Center for Advanced Computing Cornell University Ithaca NY 14853 USA Institute for Gravitational Wave Astronomy and School of Physics and Astronomy University of Birmingham Edgbaston Birmingham B15 2TT UK Institute of Cosmology Department of Physics and Astronomy Tufts University Medford MA 02155 USA Department of Physics and Astronomy West Virginia University P.O. Box 6315 Morgantown WV 26506 USA Center for Gravitational Waves and Cosmology West Virginia University Chestnut Ridge Research Building Morgantown WV 26505 USA Department of Physics University of Connecticut 196 Auditorium Road U-3046 Storrs CT 06269-3046 USA andrew.casey-clyde@uconn.edu Department of Physics and Astronomy Vanderbilt University 2301 Vanderbilt Place Nashville TN 37235 USA Department of Physics New Mexico Institute of Mining and Technology 801 Leroy Place Socorro NM 87801 USA Department of Physics Montana State University Bozeman MT 59717 USA Department of Physics and Astronomy Franklin & Marshall College P.O. Box 3003 Lancaster PA 17604 USA National Research Council Research Associate National Academy of Sciences Washington DC 20001 USA resident at Naval Research Laboratory Washington DC 20375 USA Department of Physics and Astronomy University of British Columbia 6224 Agricultural Road Vancouver BC V6T 1Z1 Canada George Mason Un

The cosmic merger history of supermassive black hole binaries (SMBHBs) is expected to produce a low-frequency gravitational wave background (GWB). Here we investigate how signs of the discrete nature of this GWB can manifest in pulsar timing arrays through excursions from, and breaks in, the expected $f_{\mathrm{GW}}^{-2/3}$ power-law of the GWB strain spectrum. To do this, we create a semi-analytic SMBHB population model, fit to NANOGrav's 15 yr GWB amplitude, and with 1,000 realizations we study the populations' characteristic strain and residual spectra. Comparing our models to the NANOGrav 15 yr spectrum, we find two interesting excursions from the power-law. The first, at $2 \; \mathrm{nHz}$, is below our GWB realizations with $p$-value significance $p = 0.05$ to $0.06$ ($\approx 1.8 \sigma - 1.9 \sigma$). The second, at $16 \; \mathrm{nHz}$, is above our GWB realizations with $p = 0.04$ to $0.15$ ($\approx 1.4 \sigma - 2.1 \sigma$). We explore the properties of a loud SMBHB which could cause such an excursion. Our simulations also show that the expected number of SMBHBs decreases by three orders of magnitude, from $\sim 10^6$ to $\sim 10^3$, between $2\; \mathrm{nHz}$ and $20 \; \mathrm{nHz}$. This causes a break in the strain spectrum as the stochasticity of the background breaks down at $26^{+28}_{-19} \; \mathrm{nHz}$, consistent with predictions pre-dating GWB measurements. The diminished GWB signal from SMBHBs at frequencies above the $26~\mathrm{nHz}$ break opens a window for PTAs to detect continuous GWs from individual SMBHBs or GWs from the early universe.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extractive Adversarial Networks for Network Embedding

Extractive Adversarial Networks for Network Embedding

引用

International Conference on Behavior, Economic and Social computing (BESC)

作者： Runxuan Chen Haoran Xie Jiaxing Chen Yanghui Rao Yingchao Zhao Fu Lee Wang School of Data and Computer Science Sun Yat-sen University Guangzhou China Department of Mathematics and Information Technology The Education University of Hong Kong Tai Po Hong Kong School of Computing and Information Sciences Caritas Institute of Higher Education Tseung kwan O Hong Kong School of Science and Technology The Open University of Hong Kong Kowloon Hong Kong

ISBN: (纸本)9781728102085;9781728102078

Network embedding has attracted more and more researchers recently. Although many algorithms focus on topological information, there exists a disadvantage. Nodes in many real-world network often have their own attributes, which are potentially valuable information, but algorithms focusing on structure ignore these messages, which will decrease the accuracy of the embedding space. To solve this problem, we consider a deep learning model. In this paper, we propose a novel model named Extractive Adversarial Networks for network embedding, which aims to extract the latent space from labels, attributed information and topological structure (e.g. low-order proximity), based on generative adversarial network model in Domain-Adversarial Training of Neural Networks. The goal of EAN is extracting the same features from the topological structure and attributed information according to our extractive network, while distinguishing the extractive features from either the topological structure or attributed information, which becomes an adversarial models. First, we train our extractive network with labels information, which is feeded with attributed information and nodes structure in vector forms. The second step is training the adversarial network to distinguish the embedding representation from either the topological structure or attributed information, where the embedding representation is from the hidden layer in extractive network. We conduct experiments on six real-world datasets, which illustrates that the proposed models outperforms state-of-the-art embedding algorithms.

关键词： Predictive models data mining Feature extraction data models Mathematical model Neural networks Computer science

来源：评论

学校读者我要写书评

暂无评论

Author Correction: The landscape of viral associations in human cancers

引用

Nature genetics 2023年第6期55卷 1077页

作者： Marc Zapatka Ivan Borozan Daniel S Brewer Murat Iskar Adam Grundhoff Malik Alawi Nikita Desai Holger Sültmann Holger Moch Colin S Cooper Roland Eils Vincent Ferretti Peter Lichter Division of Molecular Genetics German Cancer Research Center (DKFZ) Heidelberg Germany. Informatics and Bio-computing Program Ontario Institute for Cancer Research Toronto Ontario Canada. Norwich Medical School University of East Anglia Norwich UK. Earlham Institute Norwich UK. Heinrich-Pette-Institute Leibniz Institute for Experimental Virology Hamburg Germany. German Center for Infection Research (DZIF) Partner Site Hamburg-Borstel-Lübeck-Riems Hamburg Germany. Bioinformatics Core University Medical Center Hamburg-Eppendorf Hamburg Germany. Bioinformatics Group Department of Computer Science University College London London UK. Biomedical Data Science Laboratory Francis Crick Institute London UK. National Center for Tumor Diseases (NCT) Heidelberg Heidelberg Germany. Division of Cancer Genome Research German Cancer Research Center (DKFZ) Heidelberg Germany. German Cancer Consortium (DKTK) Heidelberg Germany. Department of Pathology and Molecular Pathology University and University Hospital Zürich Zurich Switzerland. Institute of Cancer Research London UK. University of East Anglia Norwich UK. Division of Theoretical Bioinformatics German Cancer Research Center (DKFZ) Heidelberg Germany. Department of Bioinformatics and Functional Genomics Institute of Pharmacy and Molecular Biotechnology Heidelberg University and BioQuant Center Heidelberg Germany. Center for Digital Health Berlin Institute of Health and Charité Universitätsmedizin Berlin Berlin Germany. Ontario Institute for Cancer Research MaRS Centre Toronto Ontario Canada. Department of Biochemistry and Molecular Medicine University of Montreal Montreal Québec Canada. Division of Molecular Genetics German Cancer Research Center (DKFZ) Heidelberg Germany. peter.lichter@dkfz-heidelberg.de. German Cancer Consortium (DKTK) Heidelberg Germany. peter.lichter@dkfz-heidelberg.de.

来源：评论

学校读者我要写书评

暂无评论

Private model compression via knowledge distillation

arXiv

引用

arXiv 2018年

作者： Wang, Ji Bao, Weidong Sun, Lichao Zhu, Xiaomin Cao, Bokai Yu, Philip S. College of Systems Engineering National University of Defense Technology Changsha China Department of Computer Science University of Illinois at Chicago Chicago United States State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China Facebook Inc. Menlo Park United States Institute for Data Science Tsinghua University Beijing China

The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs notoriously relies on increasingly complex models, which in turn is associated with an increase in computational expense far surpassing mobile devices' capacity. What is worse, app service providers need to collect and utilize a large volume of users' data, which contain sensitive information, to build the sophisticated DNN models. Directly deploying these models on public mobile devices presents prohibitive privacy risk. To benefit from the on-device deep learning without the capacity and privacy concerns, we design a private model compression framework RONA. Following the knowledge distillation paradigm, we jointly use hint learning, distillation learning, and self learning to train a compact and fast neural network. The knowledge distilled from the cumbersome model is adaptively bounded and carefully perturbed to enforce differential privacy. We further propose an elegant query sample selection method to reduce the number of queries and control the privacy loss. A series of empirical evaluations as well as the implementation on an Android mobile device show that RONA can not only compress cumbersome models efficiently but also provide a strong privacy guarantee. For example, on SVHN, when a meaningful (9:83;10-6)-differential privacy is guaranteed, the compact model trained by RONA can obtain 20× compression ratio and 19× speed-up with merely 0.97% accuracy loss. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A question answering approach to emotion cause extraction

A question answering approach to emotion cause extraction

引用

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Gui, Lin Hu, Jiannan He, Yulan Xu, Ruifeng Lu, Qin Du, Jiachen Shenzhen Graduate School Harbin Institute of Technology China College of Mathematics and Computer Science Fuzhou University China School of Engineering and Applied Science Aston University United Kingdom Guangdong Provincial Engineering Technology Research Center for Data Science China Department of Computing Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9781945626838

Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by recent advances in using deep memory networks for question answering (QA), we propose a new approach which considers emotion cause identification as a reading comprehension task in QA. Inspired by convolutional neural networks, we propose a new mechanism to store relevant context in different memory slots to model context information. Our proposed approach can extract both word level sequence features and lexical features. Performance evaluation shows that our method achieves the state-of-the-art performance on a recently released emotion cause dataset, outperforming a number of competitive baselines by at least 3.01% in F-measure. © 2017 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

MRI-based brain tumor segmentation using Gaussian mixture model with reversible jump Markov chain Monte Carlo algorithm

引用

AIP Conference Proceedings 2019年第1期2194卷

作者： Anindya Apriliyanti Pravitasari Yusuf Puji Hermanto Nur Iriawan Irhamah Kartika Fithriasari Santi Wulan Purnami Widiana Ferriastuti 1Department of Statistics Faculty of Mathematics and Natural Sciences Universitas Padjajaran 45363 Bandung Indonesia 2Department of Statistics Faculty of Mathematics Computing and Data Science Institut Teknologi Sepuluh Nopember 60111 Surabaya Indonesia 3Department of Radiology Faculty of MedicineUniversitas Airlangga 60115 Surabaya Indonesia

A brain tumor is the 15th deadly disease in Indonesia according to the WHO in 2018. In medical treatment, brain tumors can be detected through Magnetic Resonance Imaging (MRI). The main problem is how to separate the brain tumor area as the Region of interest (ROI) with the other healthy part (Non-ROI) in the MRI. In the computational statistics, a method used in image segmentation is cluster analysis. Model-Based Clustering with Gaussian Mixture Model (GMM) is often used to find the cluster where the tumor is placed. The EM Algorithm and Bayesian coupled with Markov chain Monte Carlo (MCMC) could be used to optimize the GMM. However, both EM and Bayesian MCMC are assumed that the number of clusters is fixed. Therefore, to select the optimum number of clusters, we have to use certain cluster selection criteria. This process makes the segmentation quite complicated and is not automatic. This study tries to employ the GMM using Reversible Jump Markov Chain Monte Carlo Algorithm (GMM-RJMCMC) to segment the MRI-based brain tumor and compare it with the GMM-MCMC. The use of RJMCMC is expected to accelerate the calculation process, which can provide the number of optimum clusters automatically; moreover, the MRI image segmentation could become more adaptive. The result shows that from the Correct Classification Ratio (CCR), the GMM-RJMCMC could provide an equal segmentation results compared to the GMM-MCMC, however, GMM-RJMCMC has the advantage, that is faster in executing the algorithm, this makes GMM-RJMCMC more efficient in finding the optimum number of clusters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not just privacy: Improving performance of private deep learning in mobile cloud

arXiv

引用

arXiv 2018年

作者： Wang, Ji Zhang, Jianguo Bao, Weidong Zhu, Xiaomin Cao, Bokai Yu, Philip S. College of Systems Engineering National University of Defense Technology Changsha China Department of Computer Science University of Illinois at Chicago Chicago United States College of Systems Engineering State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China Facebook Inc. Menlo Park United States Department of Computer Science University of Illinois at Chicago Chicago United States Institute for Data Science Tsinghua University Beijing China

The increasing demand for on-device deep learning services calls for a highly efficient manner to deploy deep neural networks (DNNs) on mobile devices with limited capacity. The cloud-based solution is a promising approach to enabling deep learning applications on mobile devices where the large portions of a DNN are offloaded to the cloud. However, revealing data to the cloud leads to potential privacy risk. To benefit from the cloud data center without the privacy risk, we design, evaluate, and implement a cloud-based framework Arden which partitions the DNN across mobile devices and cloud data centers. A simple data transformation is performed on the mobile device, while the resource-hungry training and the complex inference rely on the cloud data center. To protect the sensitive information, a lightweight privacy-preserving mechanism consisting of arbitrary data nullification and random noise addition is introduced, which provides strong privacy guarantee. A rigorous privacy budget analysis is given. Nonetheless, the private perturbation to the original data inevitably has a negative impact on the performance of further inference on the cloud side. To mitigate this influence, we propose a noisy training method to enhance the cloud-side network robustness to perturbed data. Through the sophisticated design, Arden can not only preserve privacy but also improve the inference performance. To validate the proposed Arden, a series of experiments based on three image datasets and a real mobile application are conducted. The experimental results demonstrate the effectiveness of Arden. Finally, we implement Arden on a demo system to verify its practicality. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GSTARIX Model for Forecasting Spatio-Temporal data with Trend, Seasonal and Intervention

引用

Journal of Physics: Conference Series 2018年第1期1097卷

作者： M A Novianto Suhartono D D Prastyo A Suharsono Setiawan Department of Statistics Faculty of Mathematics Computing and Data Science Institut Teknologi Sepuluh Nopember Surabaya Indonesia

Generalized Space-Time Autoregressive (GSTAR) is a statistics model that usually applied for forecasting data that have both spatial and temporal dependency. The monthly tourist arrival data in some locations are example of spatio-temporal data. Most of previous researches in GSTAR model only focused on stationary data. Otherwise, tourist arrival data in Indonesia mostly contain trend, seasonal, and some extreme values caused by interventions or outliers. The objective of this study is to apply and develop GSTAR model for forecasting spatio-temporal data with trend, seasonal, and interventions or outliers. This model is then known as GSTAR with exogeneous variables or GSTARIX model. Then, the forecast accuracy of GSTARIX model are compared to VAR with exogenous variables or VARIX model. Monthly data about number of tourist arrivals to Jakarta, Surakarta, Surabaya, and Denpasar are used as case study. Moreover, two methods are used for parameter estimation, i.e. Ordinary Least Square (OLS) and Generalized Least Square (GLS). The criteria for selecting the best model is Root Mean Square Error (RMSE). The results showed that the best model for forecasting tourist arrivals in each location are different. The best model for forecasting number of tourist arrivals to Jakarta and Surabaya is GSTARIX with OLS method or GSTARIX-OLS. Whereas, the best model for Denpasar and Surakarta data are VARIX and GSTARIX-GLS, respectively.

关键词：

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：