检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Li, Qianxiao Chen, Long Tai, Cheng Weinan, E. Institute of High Performance Computing Agency for Science Technology and Research 1 Fusionopolis Way Connexis North138632 Singapore Beijing Institute of Big Data Research Peking University Beijing100080 China Princeton University PrincetonNJ08544 United States

The continuous dynamical system approach to deep learning is explored in order to devise alternative frameworks for training algorithms. Training is recast as a control problem and this allows us to formulate necessary optimality conditions in continuous time using the Pontryagin's maximum principle (PMP). A modification of the method of successive approximations is then used to solve the PMP, giving rise to an alternative training algorithm for deep learning. This approach has the advantage that rigorous error estimates and convergence results can be established. We also show that it may avoid some pitfalls of gradient-based methods, such as slow convergence on at landscapes near saddle points. Furthermore, we demonstrate that it obtains favorable initial convergence rate periteration, provided Hamiltonian maximization can be efficiently carried out - a step which is still in need of improvement. Overall, the approach opens up new avenues to attack problems associated with deep learning, such as trapping in slow manifolds and inapplicability of gradient-based methods for discrete trainable variables. 68T05, 49D, 49M Copyright © 2017, The Authors. All rights reserved.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

Match-SRNN: Modeling the recursive matching structure with spatial RNN 25

Match-SRNN: Modeling the recursive matching structure with s...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Wan, Shengxian Lan, Yanyan Xu, Jun Guo, Jiafeng Pang, Liang Xueqi, Cheng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i.e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Predict anchor links across social networks via an embedding approach 25

Predict anchor links across social networks via an embedding...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Man, Tong Shen, Huawei Liu, Shenghua Jin, Xiaolong Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Predicting anchor links across social networks has important implications to an array of applications, including cross-network information diffusion and cross-domain recommendation. One challenging problem is: whether and to what extent we can address the anchor link prediction problem, if only structural information of networks is available. Most existing methods, unsupervised or supervised, directly work on networks themselves rather than on their intrinsic structural regularities, and thus their effectiveness is sensitive to the high dimension and sparsity of networks. To offer a robust method, we propose a novel supervised model, called PALE, which employs network embedding with awareness of observed anchor links as supervised information to capture the major and specific structural regularities and further learns a stable cross-network mapping for predicting anchor links. Through extensive experiments on two realistic datasets, we demonstrate that PALE significantly outperforms the state-of-the-art methods.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Output statistics of quantum annealers with disorder

arXiv

引用

arXiv 2018年

作者： Brugger, Jonathan Seidel, Christian Streif, Michael Wudarski, Filip A. Dittel, Christoph Buchleitner, Andreas Physikalisches Institut Albert-Ludwigs-Universität Freiburg Herrmann-Herder-Straße 3 FreiburgD-79104 Germany Data:Lab Volkswagen Group Ungererstr. 69 München80805 Germany Institute of Physics Faculty of Physics Astronomy and Informatics Nicolaus Copernicus University Grudziądzka 5/7 Toruń87–100 Poland EUCOR Centre for Quantum Science and Quantum Computing Albert-Ludwigs-Universität Freiburg Herrmann-Herder-Straße 3 FreiburgD-79104 Germany

We demonstrate that the output statistics of a standard quantum annealing protocol run on D-Wave 2000Q can be mimicked by static disorder garnishing an otherwise ideal device hardware – for a 10-qubit toy Hamiltonian as well as for problem instances with thousands of qubits. A Boltzmann-like distribution over distinct output states is shown to emerge with increasing disorder strength. Copyright © 2018, The Authors. All rights reserved.

关键词： Toys

来源：评论

学校读者我要写书评

暂无评论

EyeQual: Accurate, Explainable, Retinal Image Quality Assessment

EyeQual: Accurate, Explainable, Retinal Image Quality Assess...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Pedro Costa Aurelio Campilho Bryan Hooi Asim Smailagic Kris Kitani Shenghua Liu Christos Faloutsos Adrian Galdran Department of Electrical and Computer Engineering Carnegie Mellon University INESC TEC Porto Faculty of Engineering University of Porto Department of Statistics and Data Science Carnegie Mellon University Robotics Institute Carnegie Mellon University Chinese Academy of Sciences Institute of Computing Technology China School of Computer Science Carnegie Mellon University

Given a retinal image, can we automatically determine whether it is of high quality (suitable for medical diagnosis)? Can we also explain our decision, pinpointing the region or regions that led to our decision? Images from human retinas are vital for the diagnosis of multiple health issues, like hypertension, diabetes, and Alzheimer's; low quality images may force the patient to come back again for a second scanning, wasting time and possibly delaying treatment. However, existing retinal image quality assessment methods are either black boxes without explanations of the results or depend heavily on feature engineering or on complex and error-prone anatomical structures' segmentation. Therefore, we propose EyeQual, that solves exactly this problem. EyeQual is novel, fast for inference, accurate and explainable, pinpointing low-quality regions on the image. We evaluated EyeQual on two real datasets where it achieved 100% accuracy taking just 36 milliseconds for each image.

关键词： Retina Image quality Diabetes Standards Retinopathy Machine learning Graphical models

来源：评论

学校读者我要写书评

暂无评论

Comparison of Polarized Radiative Transfer Codes Used by the EHT Collaboration

引用

The Astrophysical Journal 2023年第1期950卷 35-35页

作者： Ben S. Prather Jason Dexter Monika Moscibrodzka Hung-Yi Pu Thomas Bronzwaer Jordy Davelaar Ziri Younsi Charles F. Gammie Roman Gold George N. Wong Kazunori Akiyama Antxon Alberdi Walter Alef Juan Carlos Algaba Richard Anantua Keiichi Asada Rebecca Azulay Uwe Bach Anne-Kathrin Baczko David Ball Mislav Baloković John Barrett Michi Bauböck Bradford A. Benson Dan Bintley Lindy Blackburn Raymond Blundell Katherine L. Bouman Geoffrey C. Bower Hope Boyce Michael Bremer Christiaan D. Brinkerink Roger Brissenden Silke Britzen Avery E. Broderick Dominique Broguiere Sandra Bustamante Do-Young Byun John E. Carlstrom Chiara Ceccobello Andrew Chael Chi-kwan Chan Dominic O. Chang Koushik Chatterjee Shami Chatterjee Ming-Tang Chen Yongjun Chen Xiaopeng Cheng Ilje Cho Pierre Christian Nicholas S. Conroy John E. Conway James M. Cordes Thomas M. Crawford Geoffrey B. Crew Alejandro Cruz-Osorio Yuzhu Cui Mariafelicia De Laurentis Roger Deane Jessica Dempsey Gregory Desvignes Vedant Dhruv Sheperd S. Doeleman Sean Dougal Sergio A. Dzib Ralph P. Eatough Razieh Emami Heino Falcke Joseph Farah Vincent L. Fish Ed Fomalont H. Alyson Ford Raquel Fraga-Encinas William T. Freeman Per Friberg Christian M. Fromm Antonio Fuentes Peter Galison Roberto García Olivier Gentaz Boris Georgiev Ciriaco Goddi Arturo I. Gómez-Ruiz José L. Gómez Minfeng Gu Mark Gurwell Kazuhiro Hada Daryl Haggard Kari Haworth Michael H. Hecht Ronald Hesper Dirk Heumann Luis C. Ho Paul Ho Mareki Honma Chih-Wei L. Huang Lei Huang David H. Hughes Shiro Ikeda C. M. Violette Impellizzeri Makoto Inoue Sara Issaoun David J. James Buell T. Jannuzi Michael Janssen Britton Jeter Wu Jiang Alejandra Jiménez-Rosales Michael D. Johnson Svetlana Jorstad Abhishek V. Joshi Taehyun Jung Mansour Karami Ramesh Karuppusamy Tomohisa Kawashima Garrett K. Keating Mark Kettenis Dong-Jin Kim Jae-Young Kim Jongsoo Kim Junhan Kim Motoki Kino Jun Yi Koay Prashant Kocherlakota Yutaro Kofuji Shoko Koyama Carsten Kramer Michael Kramer Thomas P. Krichbaum Cheng-Yu Kuo Noemi La Bella Tod R. Lauer Daeyoung L CCS-2 Los Alamos National Laboratory P.O. Box 1663 Los Alamos NM 87545 USA bprather@lanl.gov JILA and Department of Astrophysical and Planetary Sciences University of Colorado Boulder CO 80309 USA Department of Astrophysics/IMAPP Radboud University P.O. Box 9010 6500 GL Nijmegen The Netherlands Department of Physics National Taiwan Normal University No. 88 Sec.4 Tingzhou Road Taipei 116 Taiwan R.O.C. Center of Astronomy and Gravitation National Taiwan Normal University No. 88 Sec. 4 Tingzhou Road Taipei 116 Taiwan R.O.C. Institute of Astronomy and Astrophysics Academia Sinica 11F of Astronomy-Mathematics Building AS/NTU No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan R.O.C. Department of Astronomy and Columbia Astrophysics Laboratory Columbia University 550 W. 120th Street New York NY 10027 USA Center for Computational Astrophysics Flatiron Institute 162 Fifth Avenue New York NY 10010 USA Department of Astrophysics Institute for Mathematics Astrophysics and Particle Physics (IMAPP) Radboud University P.O. Box 9010 6500 GL Nijmegen The Netherlands Mullard Space Science Laboratory University College London Holmbury St. Mary Dorking Surrey RH5 6NT UK Institut für Theoretische Physik Goethe-Universität Frankfurt Max-von-Laue-Straße 1 D-60438 Frankfurt am Main Germany Department of Physics University of Illinois 1110 West Green Street Urbana IL 61801 USA Department of Astronomy University of Illinois at Urbana-Champaign 1002 West Green Street Urbana IL 61801 USA NCSA University of Illinois 1205 W. Clark Street Urbana IL 61801 USA CP3-Origins University of Southern Denmark Campusvej 55 DK-5230 Odense M Denmark School of Natural Sciences Institute for Advanced Study 1 Einstein Drive Princeton NJ 08540 USA Princeton Gravity Initiative Princeton University Princeton NJ 08544 USA Massachusetts Institute of Technology Haystack Observatory 99 Millstone Road Westford MA 01886 USA National Astronomical Observatory of Japan 2-21-1 Osaw

Interpretation of resolved polarized images of black holes by the Event Horizon Telescope (EHT) requires predictions of the polarized emission observable by an Earth-based instrument for a particular model of the black hole accretion system. Such predictions are generated by general relativistic radiative transfer (GRRT) codes, which integrate the equations of polarized radiative transfer in curved spacetime. A selection of ray-tracing GRRT codes used within the EHT Collaboration is evaluated for accuracy and consistency in producing a selection of test images, demonstrating that the various methods and implementations of radiative transfer calculations are highly consistent. When imaging an analytic accretion model, we find that all codes produce images similar within a pixel-wise normalized mean squared error (NMSE) of 0.012 in the worst case. When imaging a snapshot from a cell-based magnetohydrodynamic simulation, we find all test images to be similar within NMSEs of 0.02, 0.04, 0.04, and 0.12 in Stokes I, Q, U, and V, respectively. We additionally find the values of several image metrics relevant to published EHT results to be in agreement to much better precision than measurement uncertainties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Publisher Correction: Extreme risk induced by communities in interdependent networks

引用

Communications Physics 2019年第1期2卷 1页

作者： Jiachen Sun Rui Zhang Ling Feng Christopher Monterola Xiao Ma Céline Rozenblat H. Eugene Stanley Boris Podobnik Yanqing Hu School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Institute for Molecular Engineering University of Chicago Chicago USA Institute of High Performance Computing A*STAR Singapore Singapore Department of Physics National University of Singapore Singapore Singapore Asian Institute of Management Metro Manila Philippines School of Data and Computer Science Sun Yat-sen University Guangzhou China Institute of Geography University of Lausanne Lausanne Switzerland Department of Physics Boston University Boston USA Faculty of Civil Engineering University of Rijeka Rijeka Croatia Faculty of Information Studies Novo Mesto Slovenia Zagreb School of Economics and Management Zagreb Croatia Luxembourg School of Business Luxembourg Luxembourg

来源：评论

学校读者我要写书评

暂无评论

Monte Carlo approximation certificates for k-means clustering

arXiv

引用

arXiv 2017年

作者： Mixon, Dustin G. Villar, Soledad Department of Mathematics Ohio State University ColumbusOH United States Center for Data Science New York University New YorkNY United States Simons Institute for Computing Uc Berkeley BerkeleyCA United States

Efficient algorithms for k-means clustering frequently converge to suboptimal partitions, and given a partition, it is difficult to detect k-means optimality. In this paper, we develop an a posteriori certifier of approximate optimality for k-means clustering. The certifier is a sublinear Monte Carlo algorithm based on Peng and Wei's semidefinite relaxation of k-means. In particular, solving the relaxation for small random samples of the data set produces a highconfidence lower bound on the k-means objective, and being sub-linear, our algorithm is faster than k-means++ when the number of data points is large. We illustrate the performance of our algorithm with both numerical experiments and a performance guarantee: If the data points are drawn independently from any mixture of two Gaussians over mwith identity covariance, then with probability 1O(1=m), our poly(m)-time algorithm produces a 3-approximation certificate with 99% confidence. Copyright © 2017, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Stable quantum memories with limited measurement

引用

Physical Review A 2018年第3期98卷 032322-032322页

作者： C. Daniel Freeman Mohan Sarovar C. M. Herdman K. B. Whaley Berkeley Quantum Information & Computation Center University of California Berkeley California 94720 USA Department of Physics University of California Berkeley California 94720 USA Extreme-scale Data Science and Analytics Sandia National Laboratories Livermore California 94550 USA Institute for Quantum Computing University of Waterloo Waterloo Ontario N2L 3G1 Canada Department of Chemistry University of Waterloo Waterloo Ontario N2L 3G1 Canada Department of Physics & Astronomy University of Waterloo Waterloo Ontario N2L 3G1 Canada Department of Chemistry University of California Berkeley California 94720 USA

We demonstrate the existence of a finite temperature threshold for a one-dimensional stabilizer code under an error correcting protocol that requires only a fraction of the syndrome measurements. Below the threshold temperature, encoded states have exponentially long lifetimes, as demonstrated by numerical and analytical arguments. We sketch how this algorithm generalizes to higher-dimensional stabilizer codes with stringlike excitations, such as the toric code.

关键词： Quantum error correction Quantum memories

来源：评论

学校读者我要写书评

暂无评论

Learning a wavelet-like auto-encoder to accelerate deep neural networks

arXiv

引用

arXiv 2017年

作者： Chen, Tianshui Lin, Liang Zuo, Wangmeng Luo, Xiaonan Zhang, Lei School of Data and Computer Science Sun Yat-sen University Guangzhou China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Department of Computing Hong Kong Polytechnic University Hong Kong SenseTime Group Limited

Accelerating deep neural networks (DNNs) has been attracting increasing attention as it can benefit a wide range of applications, e.g., enabling mobile systems with limited computing resources to own powerful visual recognition ability. A practical strategy to this goal usually relies on a two-stage process: operating on the trained DNNs (e.g., approximating the convolutional filters with tensor decomposition) and fine-tuning the amended network, leading to difficulty in balancing the trade-off between acceleration and maintaining recognition performance. In this work, aiming at a general and comprehensive way for neural network acceleration, we develop a Wavelet-like Auto-Encoder (WAE) that decomposes the original input image into two low-resolution channels (sub-images) and incorporate the WAE into the classification neural networks for joint training. The two decomposed channels, in particular, are encoded to carry the low-frequency information (e.g., image profiles) and high-frequency (e.g., image details or noises), respectively, and enable reconstructing the original input image through the decoding process. Then, we feed the low-frequency channel into a standard classification network such as VGG or ResNet and employ a very lightweight network to fuse with the high-frequency channel to obtain the classification result. Compared to existing DNN acceleration solutions, our framework has the following advantages: i) it is tolerant to any existing convolutional neural networks for classification without amending their structures;ii) the WAE provides an interpretable way to preserve the main components of the input image for classification. Copyright © 2017, 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

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：