检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Osia, Seyed Ali Shamsabadi, Ali Shahin Sajadmanesh, Sina Taheri, Ali Katevas, Kleomenis Rabiee, Hamid R. Lane, Nicholas D. Haddadi, Hamed Department of Computer Engineering Sharif University of Technology Iran School of Electronic Engineering and Computer Science Queen Mary University of London Faculty of Engineering Imperial College London Samsung AI Center University of Oxford

Internet of Things (IoT) devices and applications are being deployed in our homes and workplaces and in our daily lives. These devices often rely on continuous data collection and machine learning models for analytics and actuations. However, this approach introduces a number of privacy and efficiency challenges, as the service operator can perform arbitrary inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a hybrid approach for breaking down large, complex deep neural networks for cooperative, privacy-preserving analytics. To this end, instead of performing the whole operation on the cloud, we let an IoT device to run the initial layers of the neural network, and then send the output to the cloud to feed the remaining layers and produce the final result. We manipulate the model with Siamese fine-tuning and propose a noise addition mechanism to ensure that the output of the user's device contains no extra information except what is necessary for the main task, preventing any secondary inference on the data. We then evaluate the privacy benefits of this approach based on the information exposed to the cloud service. We also asses the local inference cost of different layers on a modern handset. Our evaluations show that by using Siamese fine-tuning and at a small processing cost, we can greatly reduce the level of unnecessary, potentially sensitive information in the personal data, and thus achieving the desired trade-off between utility, privacy and performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Coordinating human and agent behavior in collective-risk scenarios 31

Coordinating human and agent behavior in collective-risk sce...

引用

31st AAai Conference on Artificial Intelligence, AAai 2017

作者： Domingos, Elias Fernández Burguillo, Juan Carlos Nowé, Ann Lenaerts, Tom AI Lab. Computer Science Department Vrije Universiteit Brussel Pleinlaan 2 Brussels1050 Belgium MLG Département d'Informatique Université Libre de Bruxelles Boulevard du Triomphe CP212 Brussels1050 Belgium Department of Telematic Engineering University of Vigo Vigo36310 Spain

Various social situations entail a collective risk. A well-known example is climate change, wherein the risk of a future environmental disaster clashes with the immediate economic interest of developed and developing countries. The collective-risk game operationalizes this kind of situations. The decision process of the participants is determined by how good they are in evaluating the probability of future risk as well as their ability to anticipate the actions of the opponents. Anticipatory behavior contrasts with the reactive theories often used to analyze social dilemmas. Our initial work can already show that anticipative agents are a better model to human behavior than reactive ones. All the agents we studied used a recurrent neural network, however, only the ones that used it to predict future outcomes (anticipative agents) were able to account for changes in the context of games, a behavior also observed in experiments with humans. This extended abstract aims to explain how we wish to investigate anticipation within the context of the collective-risk game and the relevance these results may have for the field of hybrid socio-technical systems. Copyright © 2017, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

Nearest Neighbor Density Functional Estimation from Inverse Laplace Transform

arXiv

引用

arXiv 2018年

作者： Ryu, J. Jon Ganguly, Shouvik Kim, Young-Han Noh, Yung-Kyun Lee, Daniel D. Department of Electrical and Computer Engineering University of California San Diego La Jolla CA92093 United States XCOM Labs San DiegoCA92121 United States Gauss Labs Inc Seoul Korea Republic of Department of Computer Science Hanyang University Seoul04763 Korea Republic of School of Computational Sciences Korea Institute for Advanced Study Seoul02455 Korea Republic of Cornell Tech New YorkNY10044 United States Global AI Center for Samsung Research

A new approach to L2-consistent estimation of a general density functional using k-nearest neighbor distances is proposed, where the functional under consideration is in the form of the expectation of some function f of the densities at each point. The estimator is designed to be asymptotically unbiased, using the convergence of the normalized volume of a k-nearest neighbor ball to a Gamma distribution in the large-sample limit, and naturally involves the inverse Laplace transform of a scaled version of the function f. Some instantiations of the proposed estimator recover existing k-nearest neighbor based estimators of Shannon and Rényi entropies and Kullback–Leibler and Rényi divergences, and discover new consistent estimators for many other functionals such as logarithmic entropies and divergences. The L2-consistency of the proposed estimator is established for a broad class of densities for general functionals, and the convergence rate in mean squared error is established as a function of the sample size for smooth, bounded densities. Copyright © 2018, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Latent heterogeneous multilayer community detection

arXiv

引用

arXiv 2018年

作者： Ali, Hafiz Tiomoko Liu, Sijia Yilmáz, Yasin Hero, Alfred Couillet, Romain Rajapakse, Indika Laboratoire des Signaux et Systèmes CentraleSupélec Gif-Sur-Yvette91192 France AI Learning IBM CambridgeMA United States Electrical Engineering Department University of South Florida TampaFL United States Electrical Engineering and Computer Science University of Michigan Ann ArborMI48105 United States Computational Medicine and Bioinformatics University of Michigan Ann ArborMI48105 United States

We propose a method for simultaneously detecting shared and unshared communities in heterogeneous multilayer weighted and undirected networks. The multilayer network is assumed to follow a generative probabilistic model that takes into account the similarities and dissimilarities between the communities. We make use of a variational Bayes approach for jointly inferring the shared and unshared hidden communities from multilayer network observations. We show the robustness of our approach compared to state-of-the art algorithms in detecting disparate (shared and private) communities on synthetic data as well as on real genome-wide fibroblast proliferation dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Multilayers

来源：评论

学校读者我要写书评

暂无评论

Stylizing face images via multiple exemplars

arXiv

引用

arXiv 2017年

作者： Song, Yibing Bao, Linchao He, Shengfeng Yang, Qingxiong Yang, Ming-Hsuan Department of Computer Science City University of Hong Kong Tencent AI Lab South China University of Technology School of Information Science and Technology University of Science and Technology of China Electrical Engineering and Computer Science University of California at Merced

We address the problem of transferring the style of a headshot photo to face images. Existing methods using a single exemplar lead to inaccurate results when the exemplar does not contain sufficient stylized facial components for a given photo. In this work, we propose an algorithm to stylize face images using multiple exemplars containing different subjects in the same style. Patch correspondences between an input photo and multiple exemplars are established using a Markov Random Field (MRF), which enables accurate local energy transfer via Laplacian stacks. As image patches from multiple exemplars are used, the boundaries of facial components on the target image are inevitably inconsistent. The artifacts are removed by a post-processing step using an edge-preserving filter. Experimental results show that the proposed algorithm consistently produces visually pleasing results. Copyright © 2017, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs

arXiv

引用

arXiv 2019年

作者： Orlando, Jose Ignacio Fu, Huazhu Breda, Jo-Ao Barbossa Keer, Karelvan Bathula, Deepti R. Diaz-Pinto, Andres Fang, Ruogu Heng, Pheng-Ann Kim, Jeyoung Lee, JoonHo Lee, Joonseok Li, Xiaoxiao Liu, Peng Lu, Shuai Murugesan, Balamurali Naranjo, Valery Phaye, Sai Samarth R. Shankaranarayana, Sharath M. Sikka, Apoorva Son, Jaemin Hengel, Antonvanden Wang, Shujun Wu, Junyan Wu, Zifeng Xu, Guanghui Xu, Yongli Yin, Pengshuai Li, Fei Zhang, Xiulan Xu, Yanwu Bogunovic, Hrvoje Department of Ophthalmology and Optometry Medical University of Vienna Spitalgasse 23 Vienna1090 Australia Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates Surgery and Physiology Department Ophthalmology Unit Faculty of Medicine University of Porto Porto Research Group Ophthalmology KU Leuven Leuven Belgium Ropar Rupnagar140001 India Instituto de Investigacione Innovacion en Bioingeniera Universitat Politecnica de Valencia Valencia46022 Spain J. Crayton Pruitt Family Dept. of Biomedical Engineering University of Florida 32611 United States Department of Computer Science and Engineering Chinese University of Hong Kong 999077 Hong Kong Gachon University Gyeonggi-Do461-701 Korea Republic of Samsung SDS AI Research Center Seoul06765 Korea Republic of Yale University New HavenCT06510 United States Faculty of Science Beijing University of Chemical Technology Beijing100029 China Healthcare Technology Innovation Centre IIT Madras India Department of Electrical Engineering IIT Madras India VUNO Inc Seoul137-810 Korea Republic of Australian Institute for Machine Learning Australia Cleerly Inc New YorkNY10022 United States South China University of Technology Guangzhou510006 China Zhongshan Ophthalmic Center Sun Yat-sen University Guangzhou Shi China Articial Intelligence Innovation Business Baidu Inc China and Cixi Institute of Bio Medical Engineering Chinese Academy of Sciences China

Glaucoma is one of the leading causes of irreversible but preventable blindness in working age populations. Color fundus photography (CFP) is the most cost-effective imaging modality to screen for retinal disorders. However, its application to glaucoma has been limited to the computation of a few related biomarkers such as the vertical cup-to-disc ratio. Deep learning approaches, although widely applied for medical image analysis, have not been extensively used for glaucoma assessment due to the limited size of the available data sets. Furthermore, the lack of a standardize benchmark strategy makes dificult to compare existing methods in a uniform way. In order to overcome these issues we set up the Retinal Fundus Glaucoma Challenge, REFUGE (http://***), held in conjunction with MICCai 2018. The challenge consistedof two primary tasks, namely optic disc/cup segmentation and glaucoma classification. As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one. We have also built an evaluation framework to ease and ensure fairness in the comparison of different models, encouraging the development of novel techniques in the field. 12 teams qualified and participated in the online challenge. This paper summarizes their methods and analyzes their corresponding results. In particular, we observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task. Furthermore, the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results. Copyright © 2019, arXiv, All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Author Correction: π-HuB: the proteomic navigator of the human body

引用

Nature 2025年第8046期637卷 E22页

作者： Fuchu He Ruedi Aebersold Mark S Baker Xiuwu Bian Xiaochen Bo Daniel W Chan Cheng Chang Luonan Chen Xiangmei Chen Yu-Ju Chen Heping Cheng Ben C Collins Fernando Corrales Jürgen Cox Weinan E Jennifer E Van Eyk Jia Fan Pouya Faridi Daniel Figeys George Fu Gao Wen Gao Zu-Hua Gao Keisuke Goda Wilson Wen Bin Goh Dongfeng Gu Changjiang Guo Tiannan Guo Yuezhong He Albert J R Heck Henning Hermjakob Tony Hunter Narayanan Gopalakrishna Iyer Ying Jiang Connie R Jimenez Lokesh Joshi Neil L Kelleher Ming Li Yang Li Qingsong Lin Cui Hua Liu Fan Liu Guang-Hui Liu Yansheng Liu Zhihua Liu Teck Yew Low Ben Lu Matthias Mann Anming Meng Robert L Moritz Edouard Nice Guang Ning Gilbert S Omenn Christopher M Overall Giuseppe Palmisano Yaojin Peng Charles Pineau Terence Chuen Wai Poon Anthony W Purcell Jie Qiao Roger R Reddel Phillip J Robinson Paola Roncada Chris Sander Jiahao Sha Erwei Song Sanjeeva Srivastava aihua Sun Siu Kwan Sze Chao Tang Liujun Tang Ruijun Tian Juan Antonio Vizcaíno Chanjuan Wang Chen Wang Xiaowen Wang Xinxing Wang Yan Wang Tobias Weiss Mathias Wilhelm Robert Winkler Bernd Wollscheid Limsoon Wong Linhai Xie Wei Xie Tao Xu Tianhao Xu Liying Yan Jing Yang Xiao Yang John Yates Tao Yun Qiwei Zhai Bing Zhang Hui Zhang Lihua Zhang Lingqiang Zhang Pingwen Zhang Yukui Zhang Yu Zi Zheng Qing Zhong Yunping Zhu State Key Laboratory of Medical Proteomics Beijing Proteome Research Center National Center for Protein Sciences (Beijing) Beijing Institute of Lifeomics Beijing China. hefc@***. International Academy of Phronesis Medicine (Guangdong) Guangdong China. hefc@***. Department of Biology Institute of Molecular Systems Biology ETH Zurich Zurich Switzerland. aebersold@imsb.biol.ethz.ch. Macquarie Medical School Macquarie University Sydney New South Wales Australia. Institute of Pathology and Southwest Cancer Center Southwest Hospital Third Military Medical University (Army Medical University) and Key Laboratory of Tumor Immunopathology Ministry of Education of China Chongqing China. Institute of Health Service and Transfusion Medicine Beijing China. Department of Pathology and The Sidney Kimmel Comprehensive Cancer Center Johns Hopkins University Baltimore MD USA. State Key Laboratory of Medical Proteomics Beijing Proteome Research Center National Center for Protein Sciences (Beijing) Beijing Institute of Lifeomics Beijing China. Key Laboratory of Systems Biology Center for Excellence in Molecular Cell Science Shanghai Institute of Biochemistry and Cell Biology Chinese Academy of Sciences Shanghai China. Department of Nephrology First Medical Center of Chinese PLA General Hospital Nephrology Institute of the Chinese People's Liberation Army State Key Laboratory of Kidney Diseases National Clinical Research Center for Kidney Diseases Beijing Key Laboratory of Kidney Disease Research Beijing China. Institute of Chemistry Academia Sinica Taipei China. National Biomedical Imaging Center State Key Laboratory of Membrane Biology Institute of Molecular Medicine Peking-Tsinghua Center for Life Sciences College of Future Technology Peking University Beijing China. School of Biological Sciences Queen's University of Belfast Belfast UK. Functional Proteomics Laboratory Centro Nacional de Biotecnología-CSIC Madrid Spain. Computational Systems Biochemistry Research Group Ma

来源：评论

学校读者我要写书评

暂无评论

Entropy-SGD: Biasing gradient descent into wide valleys 5

Entropy-SGD: Biasing gradient descent into wide valleys

引用

5th International Conference on Learning Representations, ICLR 2017

作者： Chaudhari, Pratik Choromanska, Anna Soatto, Stefano LeCun, Yann Baldassi, Carlo Borgs, Christian Chayes, Jennifer Sagun, Levent Zecchina, Riccardo Computer Science Department University of California Los Angeles United States Department of Electrical and Computer Engineering New York University United States Courant Institute of Mathematical Sciences New York University United States Facebook AI Research New York United States Dipartimento di Scienza Applicata e Tecnologia Politecnico di Torino Italy Microsoft Research New England Cambridge United States

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema with low generalization error have a large proportion of almost-zero eigenvalues in the Hessian with very few positive or negative eigenvalues. We leverage upon this observation to construct a local-entropy-based objective function that favors well-generalizable solutions lying in large flat regions of the energy landscape, while avoiding poorly-generalizable solutions located in the sharp valleys. Conceptually, our algorithm resembles two nested loops of SGD where we use Langevin dynamics in the inner loop to compute the gradient of the local entropy before each update of the weights. We show that the new objective has a smoother energy landscape and show improved generalization over SGD using uniform stability, under certain assumptions. Our experiments on convolutional and recurrent neural networks demonstrate that Entropy-SGD compares favorably to state-of-the-art techniques in terms of generalization error and training time. © ICLR 2019 - Conference Track Proceedings. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Hoeffding Tree Algorithms for Anomaly Detection in Streaming Datasets: A Survey

引用

Journal of Information Security 2017年第4期8卷 339-361页

作者： Asmah Muallem Sachin Shetty Jan Wei Pan Juan Zhao Biswajit Biswal Department of Electrical and Computer Engineering Tennessee State University Nashville TN USA Virginia Modeling Analysis and Simulation Center Old Dominion University Norfolk VA USA R&D Engineering Department Roadstar.AI. Mountain View CA USA Department of Electrical and Computer Engineering Tennessee State University Nashville TN USA Department of Mathematics and Computer Science South Carolina State University Orangeburg SC USA

This survey aims to deliver an extensive and well-constructed overview of using machine learning for the problem of detecting anomalies in streaming datasets. The objective is to provide the effectiveness of using Hoeffding Trees as a machine learning algorithm solution for the problem of detecting anomalies in streaming cyber datasets. In this survey we categorize the existing research works of Hoeffding Trees which can be feasible for this type of study into the following: surveying distributed Hoeffding Trees, surveying ensembles of Hoeffding Trees and surveying existing techniques using Hoeffding Trees for anomaly detection. These categories are referred to as compositions within this paper and were selected based on their relation to streaming data and the flexibility of their techniques for use within different domains of streaming data. We discuss the relevance of how combining the techniques of the proposed research works within these compositions can be used to address the anomaly detection problem in streaming cyber datasets. The goal is to show how a combination of techniques from different compositions can solve a prominent problem, anomaly detection.

关键词： Hoeffding Trees Distributed Ensembles Anomaly Detection Machine Learning Spark

来源：评论

学校读者我要写书评

暂无评论

Conditional molecular design with deep generative models

arXiv

引用

arXiv 2018年

作者： Kang, Seokho Cho, Kyunghyun Department of Systems Management Engineering Sungkyunkwan University 2066 Seobu-ro Jangan-gu Suwon16419 Korea Republic of Department of Computer Science Center for Data Science New York University 60 5th Avenue New YorkNY10011 United States Facebook AI Research 770 Broadway New YorkNY10003 United States CIFAR Azrieli Global Scholar Canadian Institute for Advanced Research 661 University Avenue TorontoONM5G 1M1 Canada

Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficiently. In this paper, we present a conditional molecular design method that facilitates generating new molecules with desired properties. The proposed model, which simultaneously performs both property prediction and molecule generation, is built as a semi-supervised variational autoencoder trained on a set of existing molecules with only a partial annotation. We generate new molecules with desired properties by sampling from the generative distribution estimated by the model. We demonstrate the effectiveness of the proposed model by evaluating it on drug-like molecules. The model improves the performance of property prediction by exploiting unlabeled molecules, and efficiently generates novel molecules fulfilling various target conditions. Copyright © 2018, The Authors. All rights reserved.

关键词： Molecules

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：