检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Xu, Qianqian Xiong, Jiechao Cao, Xiaochun Huang, Qingming Yao, Yuan Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing1000190 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Tencent AI Lab Shenzhen518057 BICMR-LMAM-LMEQF-LMP School of Mathematical Sciences Peking University Beijing100871 China University of Chinese Academy of Sciences Institute of Computing Technology of Chinese Academy of Sciences Beijing100190 China Department of Mathematics and by courtesy Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong

In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or social utility function which generates their comparison behaviors in experiments. However, in reality annotators are subject to variations due to multi-criteria, abnormal, or a mixture of such behaviors. In this paper, we propose a parsimonious mixed-effects model, which takes into account both the fixed effect that the majority of annotators follows a common linear utility model, and the random effect that some annotators might deviate from the common significantly and exhibit strongly personalized preferences. The key algorithm in this paper establishes a dynamic path from the social utility to individual variations, with different levels of sparsity on personalization. The algorithm is based on the Linearized Bregman Iterations, which leads to easy parallel implementations to meet the need of large-scale data analysis. In this unified framework, three kinds of random utility models are presented, including the basic linear model with L2 loss, Bradley-Terry model, and Thurstone-Mosteller model. The validity of these multi-level models are supported by experiments with both simulated and real-world datasets, which shows that the parsimonious multi-level models exhibit improvements in both interpretability and predictive precision compared with traditional HodgeRank. Copyright © 2018, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Non-iterative SLAM for Warehouse Robots Using Ground Textures

arXiv

引用

arXiv 2017年

作者： Xu, Kuan Yang, Zheng Xie, Lihua Wang, Chen School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Spatial AI & Robotics Lab Department of Computer Science and Engineering University at Buffalo BuffaloNY14260 United States

We present a novel visual SLAM method for the warehouse robot with a single downward-facing camera using ground textures. Traditional methods resort to feature matching or point registration for pose optimization, which easily suffers from repetitive features and poor texture quality. In this paper, we present a robust kernel cross-correlator for robust image-level registration. Compared with the existing methods that often use iterative solutions, our method, named non-iterative visual SLAM (NI-SLAM), has a closed-form solution with a complexity of O ( nlogn ). This allows it to run very efficiently, yet still provide better accuracy and robustness than the state-of-the-art methods. In the experiments, we demonstrate that it achieves 78% improvement over the state-of-the-art systems for indoor and outdoor localization. We have successfully tested it on warehouse robots equipped with a single downward camera, showcasing its product-ready superiority in a real operating area. Copyright © 2017, The Authors. All rights reserved.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

Learning with Bounded Instance-and Label-dependent Label Noise

arXiv

引用

arXiv 2017年

作者： Cheng, Jiacheng Liu, Tongliang Ramamohanarao, Kotagiri Tao, Dacheng UBTECH Sydney AI Centre and SIT FEIT.e University of Sydney Sydney Australia Department of EEIS University of Science and Technology of China Hefei China Department of Computer Science and Software Engineering The University of Melbourne Melbourne Australia

Instance-and Label-dependent label Noise (ILN) is widely existed in real-world datasets but has been rarely studied. In this paper, we focus on Bounded Instanceand Label-dependent labelNoise (BILN), a particular case of ILNwhere the label noise rates, the probabilities that the true labels of examples flip into the corrupted ones, have upper bounds. Specifically, we introduce the concept of distilled examples, i.e. examples whose labels are identical with the labels assigned for them by the Bayes optimal classifier, and prove that under certain conditions classifier learnt on distilled examples will converge to the Bayes optimal classifier. Inspired by the idea of learning with distilled examples, we then propose a learning algorithm with theoretical guarantees for its robustness to BILN. At last, empirical evaluations on both synthetic and real-world datasets show effectiveness of our algorithm in learning with BILN. Copyright © 2017, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Progressive joint modeling in unsupervised single-channel overlapped speech recognition

arXiv

引用

arXiv 2017年

作者： Chen, Zhehuai Droppo, Jasha Li, Jinyu Xiong, Wayne Computer Science and Engineering Department Shanghai Jiao Tong University Shanghai200240 China Microsoft AI and Research One Microsoft Way RedmondWA98052 United States

Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which applies a single neural network to solve this single-input, multiple-output modeling problem. We propose to advance the current state of the art by imposing a modular structure on the neural network, applying a progressive pretraining regimen, and improving the objective function with transfer learning and a discriminative training criterion. The modular structure splits the problem into three sub-tasks: frame-wise interpreting, utterance-level speaker tracing, and speech recognition. The pretraining regimen uses these modules to solve progressively harder tasks. Transfer learning leverages parallel clean speech to improve the training targets for the network. Our discriminative training formulation is a modification of standard formulations that also penalizes competing outputs of the system. Experiments are conducted on the artificial overlapped Switchboard and hub5e-swb dataset. The proposed framework achieves over 30% relative improvement of WER over both a strong jointly trained system, PIT for ASR, and a separately optimized system, PIT for speech separation with clean speech ASR model. The improvement comes from better model generalization, training efficiency and the sequence level linguistic knowledge *** Codes 68T10 Copyright © 2017, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Analysis of Information Delivery Dynamics in Cognitive Sensor Networks Using Epidemic Models

arXiv

引用

arXiv 2017年

作者： Chen, Pin-Yu Cheng, Shin-Ming Hsu, Hui-Yu AI Foundations Group IBM Thomas J. Watson Research Center Yorktown HeightsNY United States Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan

To fully empower sensor networks with cognitive Internet of Things (IoT) technology, efficient medium access control protocols that enable the coexistence of cognitive sensor networks with current wireless infrastructure are as essential as the cognitive power in data fusion and processing due to shared wireless spectrum. Cognitive radio (CR) is introduced to increase spectrum efficiency and support such an endeavor, which thereby becomes a promising building block toward facilitating cognitive IoT. In this paper, primary users (PUs) refer to devices in existing wireless infrastructure, and secondary users (SUs) refer to cognitive sensors. For interference control between PUs and SUs, SUs adopt dynamic spectrum access and power adjustment to ensure sufficient operation of PUs, which inevitably leads to increasing latency and poses new challenges on the reliability of IoT communications. To guarantee operations of primary systems while simultaneously optimizing system performance in cognitive radio ad hoc networks (CRAHNs), this paper proposes interference-aware flooding schemes exploiting global timeout and vaccine recovery schemes to control the heavy buffer occupancy induced by packet replications. The information delivery dynamics of SUs under the proposed interference-aware recovery-assisted flooding schemes is analyzed via epidemic models and stochastic geometry from a macroscopic view of the entire system. The simulation results show that our model can efficiently capture the complicated data delivery dynamics in CRAHNs in terms of end-to-end transmission reliability and buffer occupancy. This paper sheds new light on analysis of recovery-assisted flooding schemes in CRAHNs and provides performance evaluation of cognitive IoT services built upon CRAHNs. Copyright © 2017, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Fast MPEG-CDVS encoder with GPU-CPU hybrid computing

arXiv

引用

arXiv 2017年

作者： Duan, Ling-Yu Sun, Wei Zhang, Xinfeng Wang, Shiqi Chen, Jie Yin, Jianxiong See, Simon Huang, Tiejun Kot, Alex C. Gao, Wen School of Electronics Engineering and Computer Science Institute of Digital Media Peking University Beijing100871 China Lab Nanyang Technological University Singapore Department of Computer Science City University of Hong Kong Kowloon Hong Kong NVIDiA AI Tech. Centre

The compact descriptors for visual search (CDVS) standard from ISO/IEC moving pictures experts group (MPEG) has succeeded in enabling the interoperability for efficient and effective image retrieval by standardizing the bitstream syntax of compact feature descriptors. However, the intensive computation of CDVS encoder unfortunately hinders its widely deployment in industry for large-scale visual search. In this paper, we revisit the merits of low complexity design of CDVS core techniques and present a very fast CDVS encoder by leveraging the massive parallel execution resources of GPU. We elegantly shift the computation-intensive and parallel-friendly modules to the stateof- the-arts GPU platforms, in which the thread block allocation and the memory access are jointly optimized to eliminate performance loss. In addition, those operations with heavy data dependence are allocated to CPU to resolve the extra but nonnecessary computation burden for GPU. Furthermore, we have demonstrated the proposed fast CDVS encoder can work well with those convolution neural network approaches which has harmoniously leveraged the advantages of GPU platforms, and yielded significant performance improvements. Comprehensive experimental results over benchmarks are evaluated, which has shown that the fast CDVS encoder using GPU-CPU hybrid computing is promising for scalable visual search. Copyright © 2017, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Community-wide hackathons to identify central themes in single-cell multi-omics

引用

Genome biology 2021年第1期22卷 246页

作者： Kim-Anh Lê Cao Al J Abadi Emily F Davis-Marcisak Lauren Hsu Arshi Arora Alexis Coullomb Atul Deshpande Yuzhou Feng Pratheepa Jeganathan Melanie Loth Chen Meng Wancen Mu Vera Pancaldi Kris Sankaran Dario Righelli Amrit Singh Joshua S Sodicoff Genevieve L Stein-O'Brien Ayshwarya Subramanian Joshua D Welch Yue You Ricard Argelaguet Vincent J Carey Ruben Dries Casey S Greene Susan Holmes Michael I Love Matthew E Ritchie Guo-Cheng Yuan Aedin C Culhane Elana Fertig Melbourne Integrative Genomics School of Mathematics and Statistics University of Melbourne Melbourne Australia. kimanh.lecao@nimelb.edu.au. Melbourne Integrative Genomics School of Mathematics and Statistics University of Melbourne Melbourne Australia. McKusick-Nathans Institute of the Department of Genetic Medicine Johns Hopkins School of Medicine Baltimore MD USA. Data Science Dana-Farber Cancer Institute Boston MA USA. Biostatistics Harvard TH Chan School of Public Health Boston MA USA. Department of Epidemiology and Biostatistics Memorial Sloan Kettering Cancer Center New York NY USA. Centre de Recherches en Cancérologie de Toulouse (INSERM) Université Paul Sabatier III Toulouse France. Cancer Convergence Institute and Division of Quantitative Sciences Department of Oncology Sidney Kimmel Comprehensive Cancer Center Johns Hopkins University School of Medicine Baltimore MD USA. Department of Mathematics and Statistics McMaster University Hamilton Canada. Bavarian Center for Biomolecular Mass Spectrometry (BayBioMS) School of Life Sciences Technical University of Munich Munich Germany. Department of Biostatistics UNC Chapel Hill NC USA. Barcelona Supercomputing Center Barcelona Spain. Department of Statistics University of Wisconsin Madison WI USA. Department of Statistical Sciences University of Padova Padova PD Italy. Department of Pathology and Laboratory Medicine University of British Columbia Vancouver BC Canada. PROOF Centre of Excellence Vancouver BC Canada. Department of Computational Medicine and Bioinformatics University of Michigan Ann Arbor MI USA. Department of Biomedical Engineering University of Michigan Ann Arbor MI USA. Department of Neuroscience Johns Hopkins University Baltimore MD USA. Kavli Neuroscience Discovery Institute Johns Hopkins University Baltimore MD USA. Klarman Cell Observatory Broad Institute of MIT and Harvard Cambridge MA USA. Department of Computer Science and Engineering University of Michiga

来源：评论

学校读者我要写书评

暂无评论

The role of artificial intelligence in achieving the Sustainable Development Goals

arXiv

引用

arXiv 2019年

作者： Vinuesa, Ricardo Azizpour, Hossein Leite, Iolanda Balaam, Madeline Dignum, Virginia Domisch, Sami Felländer, Anna Langhans, Simone Tegmark, Max Nerini, Francesco Fuso Linné FLOW Centre KTH Mechanics StockholmSE-100 44 Sweden School of Electrical Engineering and Computer Science KTH Royal Institute Of Technology Stockholm Sweden Division of Robotics Perception and Learning School of EECS KTH Royal Institute Of Technology Stockholm Sweden Division of Media Technology and Interaction Design KTH Royal Institute of Technology Lindstedtsvägen 3 Stockholm Sweden Responsible AI Lab Umeå University UmeåSE-90358 Sweden Leibniz-Institute of Freshwater Ecology and Inland Fisheries Müggelseedamm 310 Berlin12587 Germany Division of Media Technology and Interaction Design KTH Royal Institute of Technology Lindstedtsvägen 3 Stockholm Sweden Leioa Spain Department of Zoology University of Otago 340 Great King Street Dunedin9016 New Zealand Center for Brains Minds & Machines Massachusetts Institute of Technology CambridgeMA02139 United States KTH Royal Institute of Technology Brinellvagen 68 StockholmSE-100 44 Sweden

The emergence of artificial intelligence (ai) and its progressively wider impact on many sectors across the society requires an assessment of its effect on sustainable development. Here we analyze published evidence of positive or negative impacts of ai on the achievement of each of the 17 goals and 169 targets of the 2030 Agenda for Sustainable Development. We find that ai can support the achievement of 128 targets across all SDGs, but it may also inhibit 58 targets. Notably, ai enables new technologies that improve efficiency and productivity, but it may also lead to increased inequalities among and within countries, thus hindering the achievement of the 2030 Agenda. The fast development of ai needs to be supported by appropriate policy and regulation. Otherwise, it would lead to gaps in transparency, accountability, safety and ethical standards of ai-based technology, which could be detrimental towards the development and sustainable use of ai. Finally, there is a lack of research assessing the medium- and long-term impacts of ai. It is therefore essential to reinforce the global debate regarding the use of ai and to develop the necessary regulatory insight and oversight for ai-based technologies. Copyright © 2019, The Authors. All rights reserved.

关键词： Planning

来源：评论

学校读者我要写书评

暂无评论

Multilayer spectral graph clustering via convex layer aggregation: Theory and algorithms

arXiv

引用

arXiv 2017年

作者： Chen, Pin-Yu Hero, Alfred O. AI Foundations IBM Thomas J. Watson Research Center Yorktown HeightsNY10598 United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States

Multilayer graphs are commonly used for representing different relations between entities and handing heterogeneous data processing tasks. Non-standard multilayer graph clustering methods are needed for assigning clusters to a common multilayer node set and for combining information from each layer. This paper presents a multilayer spectral graph clustering (SGC) framework that performs convex layer aggregation. Under a multilayer signal plus noise model, we provide a phase transition analysis of clustering reliability. Moreover, we use the phase transition criterion to propose a multilayer iterative model order selection algorithm (MIMOSA) for multilayer SGC, which features automated cluster assignment and layer weight adaptation, and provides statistical clustering reliability guarantees. Numerical simulations on synthetic multilayer graphs verify the phase transition analysis, and experiments on real-world multilayer graphs show that MIMOSA is competitive or better than other clustering methods. Copyright © 2017, 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

Bias-variance tradeoff of graph Laplacian regularizer

arXiv

引用

arXiv 2017年

作者： Chen, Pin-Yu Liu, Sijia AI Foudations IBM Thomas J. Watson Research Center Yorktown HeightsNY10598 United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States

This paper presents a bias-variance tradeoff of graph Laplacian regularizer, which is widely used in graph signal processing and semi-supervised learning tasks. The scaling law of the optimal regularization parameter is specified in terms of the spectral graph properties and a novel signal-to-noise ratio parameter, which suggests selecting a mediocre regularization parameter is often suboptimal. The analysis is applied to three applications, including random, band-limited, and multiple-sampled graph signals. Experiments on synthetic and real-world graphs demonstrate near-optimal performance of the established analysis. Copyright © 2017, 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

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：