人工智能学术速递[2021.12.20]

访问arxivdaily.com获取含摘要速递，更有收藏、搜索等功能，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域
同步公众号:arXiv每日学术速递，欢迎关注

cs.AI人工智能，共计35篇

【1】 An Online Data-Driven Emergency-Response Method for Autonomous Agents in Unforeseen Situations
标题：一种数据驱动的自治Agent在不可预见情况下的在线应急响应方法
链接：https://arxiv.org/abs/2112.09670
作者：Glenn Maguire,Nicholas Ketz,Praveen Pilly,Jean-Baptiste Mouret
机构： Inria, CNRS, Universit´e de Lorraine, Center for Human-Machine Collaboration, Information and Systems Sciences Laboratory, HRL Laboratories

【2】 Deep Learning for Spatiotemporal Modeling of Urbanization
标题：深度学习在城市化时空建模中的应用
链接：https://arxiv.org/abs/2112.09668
作者：Tang Li,Jing Gao,Xi Peng
机构：University of Delaware, Newark, DE
备注：Accepted by NeurIPS 2021 MLPH (Machine Learning in Public Health) Workshop; Best Paper Awarded by NeurIPS 2021 MLPH (Machine Learning in Public Health) Workshop

【3】 Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)
标题：通过马尔可夫决策过程的变分抽象提炼具有形式保证的RL策略(技术报告)
链接：https://arxiv.org/abs/2112.09655
作者：Florent Delgrange,Ann Nowé,Guillermo A. Pérez
机构： AI Lab, Vrije Universiteit Brussel, University of Antwerp – Flanders Make
备注：Accepted at AAAI 2022, technical report including supplementary material (10 pages main text, 14 pages appendix)

【4】 Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation
标题：基于伪标签自训练的局部对比损失半监督医学图像分割
链接：https://arxiv.org/abs/2112.09645
作者：Krishna Chaitanya,Ertunc Erdil,Neerav Karani,Ender Konukoglu
备注：13 pages, 4 figures, 7 tables. This article is under review at a Journal

【5】 Explanation as Question Answering based on Design Knowledge
标题：基于设计知识的问答解释
链接：https://arxiv.org/abs/2112.09616
作者：Ashok Goel,Vrinda Nandan,Eric Gregori,Sungeun An,Spencer Rugaber
机构：Design Intelligence Laboratory, School of Interactive Computing, Georgia Institute of Technology
备注：7 pages, 8 figures

【6】 Global explainability in aligned image modalities
标题：对齐图像模态的全局可解释性
链接：https://arxiv.org/abs/2112.09591
作者：Justin Engelmann,Amos Storkey,Miguel O. Bernabeu
机构：UKRI CDT Biomedical AI, University of Edinburgh, School of Informatics, Usher Institute

【7】 cgSpan: Closed Graph-Based Substructure Pattern Mining
标题：cgSpan：基于封闭图的子结构模式挖掘
链接：https://arxiv.org/abs/2112.09573
作者：Zevin Shaul,Sheikh Naaz
机构：Informatica, University of Wisconsin–Madison

【8】 CPPE-5: Medical Personal Protective Equipment Dataset
标题：CPPE-5：医用个人防护设备数据集
链接：https://arxiv.org/abs/2112.09569
作者：Rishit Dagli,Ali Mustufa Shaikh
机构：High School, Narayana Junior College, Mumbai, India, Student Community Lead, Postman Inc
备注：16 pages, 6 tables, 6 figures. Code and models are available at this https URL

【9】 Symmetry-aware Neural Architecture for Embodied Visual Navigation
标题：用于具身视觉导航的对称性感知神经结构
链接：https://arxiv.org/abs/2112.09515
作者：Shuang Liu,Takayuki Okatani
机构：Okatani Takayuki, Tohoku University, RIKEN Center for AIP

【10】 Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
标题：学习奖励机：部分可观测强化学习的研究
链接：https://arxiv.org/abs/2112.09477
作者：Rodrigo Toro Icarte,Ethan Waldie,Toryn Q. Klassen,Richard Valenzano,Margarita P. Castro,Sheila A. McIlraith
机构：Pontificia Universidad Cat´olica de Chile, Vicu˜na Mackenna , Macul, RM, Chile, University of Toronto, College St, Toronto, ON, Canada, Vector Institute, University, Toronto, ON, Canada, Ryerson University, Victoria St, Toronto, ON, Canada

【11】 Towards fuzzification of adaptation rules in self-adaptive architectures
标题：自适应体系结构中适配规则模糊化的研究
链接：https://arxiv.org/abs/2112.09468
作者：Tomáš Bureš,Petr Hnětynka,Martin Kruliš,Danylo Khalyeyev,Sebastian Hahner,Stephan Seifermann,Maximilian Walter,Robert Heinrich
机构：Charles University, Prague, Czech Republic, Karlsruhe Institute of Technology (KIT), Germany

【12】 Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents
标题：强化学习智能体偏好比较的对比解释
链接：https://arxiv.org/abs/2112.09462
作者：Jasmina Gajcin,Rahul Nair,Tejaswini Pedapati,Radu Marinescu,Elizabeth Daly,Ivana Dusparic
机构：Dusparic , Trinity College Dublin, IBM Ireland
备注：7 pages, 3 figures

【13】 Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
标题：基于交替自对偶教学的弱监督语义切分
链接：https://arxiv.org/abs/2112.09459
作者：Dingwen Zhang,Wenyuan Zeng,Guangyu Guo,Chaowei Fang,Lechao Cheng,Junwei Han
机构：The Brain and Artificial Intelligence Laboratory, Northwestern Polytechnical University, Xi’an, China, Xidian University, Xi’an, China, Zhejiang Lab, Hangzhou, China

【14】 Visual Learning-based Planning for Continuous High-Dimensional POMDPs
标题：基于可视化学习的连续高维POMDP规划
链接：https://arxiv.org/abs/2112.09456
作者：Sampada Deglurkar,Michael H. Lim,Johnathan Tucker,Zachary N. Sunberg,Aleksandra Faust,Claire J. Tomlin
机构：Department of Electrical Engineering and Computer Sciences, UC Berkeley, Department of Aerospace Engineering Science, CU Boulder, Google Research

【15】 ML Supported Predictions for SAT Solvers Performance
标题：对SAT解算器性能的ML支持预测
链接：https://arxiv.org/abs/2112.09438
作者：A. -M. Leventi-Peetz,Jörg-Volker Peetz,Martina Rohde
机构： Federal Office for Information Security, Godesberger Allee ,–, DE-, Bonn, Germany
备注：None

【16】 Can Machine Learning Tools Support the Identification of Sustainable Design Leads From Product Reviews? Opportunities and Challenges
标题：机器学习工具能支持从产品评审中识别可持续设计线索吗？机遇与挑战
链接：https://arxiv.org/abs/2112.09391
作者：Michael Saidani,Harrison Kim,Bernard Yannou
机构：Department of Industrial and Enterprise, Systems Engineering, University of Illinois at, Urbana-Champaign, Illinois, USA, Laboratoire Genie Industriel, CentraleSupélec, Université Paris Saclay, Gif-sur-Yvette, France
备注：ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Aug 2021, Virtual, United States

【17】 Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction
标题：具有深度信息交互的鲁棒点云配准全Transformer框架
链接：https://arxiv.org/abs/2112.09385
作者：Guangyan Chen,Meiling Wang,Yufeng Yue,Qingxiang Zhang,Li Yuan
机构： Beijing Institute of Technology , National University of Singapore
备注：10pages, 7figures

【18】 WebGPT: Browser-assisted question-answering with human feedback
标题：WebGPT：具有人工反馈的浏览器辅助问答
链接：https://arxiv.org/abs/2112.09332
作者：Reiichiro Nakano,Jacob Hilton,Suchir Balaji,Jeff Wu,Long Ouyang,Christina Kim,Christopher Hesse,Shantanu Jain,Vineet Kosaraju,William Saunders,Xu Jiang,Karl Cobbe,Tyna Eloundou,Gretchen Krueger,Kevin Button,Matthew Knight,Benjamin Chess,John Schulman
机构：OpenAI
备注：30 pages

【19】 Dilemma of the Artificial Intelligence Regulatory Landscape
标题：人工智能管制景观的困境
链接：https://arxiv.org/abs/2112.09325
作者：Weiyue Wu,Shaoshan Liu
机构：PerceptIn

【20】 Optimal discharge of patients from intensive care via a data-driven policy learning framework
标题：通过数据驱动的政策学习框架优化重症监护患者的放电
链接：https://arxiv.org/abs/2112.09315
作者：Fernando Lejarza,Jacob Calvert,Misty M Attwood,Daniel Evans,Qingqing Mao
机构：Dascena, Inc., Sowden Road, Suite B, Houston, TX ,-, USA, McKetta Department of Chemical Engineering, The University of Texas at Austin, Austin, TX

【21】 Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages
标题：2021年HASOC火灾中的子路径概览：英语和印度雅利安语言中的仇恨言论和攻击性内容识别
链接：https://arxiv.org/abs/2112.09301
作者：Thomas Mandl,Sandip Modha,Gautam Kishore Shahi,Hiren Madhu,Shrey Satapara,Prasenjit Majumder,Johannes Schaefer,Tharindu Ranasinghe,Marcos Zampieri,Durgesh Nandini,Amit Kumar Jaiswal
机构：University of Hildesheim, Germany, LDRP-ITR, Gandhinagar, India, University of Duisburg-Essen, Germany, Indian Institute of Science, Bangalore, India, DA-IICT, Gandhinagar, India, University of Wolverhampton, United Kingdom, Rochester Institute of Technology, USA

【22】 PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision
标题：PeopleSansPeople：以人为中心的计算机视觉合成数据生成器
链接：https://arxiv.org/abs/2112.09290
作者：Salehe Erfanian Ebadi,You-Cyuan Jhang,Alex Zook,Saurav Dhakad,Adam Crespi,Pete Parisi,Steven Borkman,Jonathan Hogins,Sujoy Ganguly
机构：Unity Technologies
备注：PeopleSansPeople template Unity environment, benchmark binaries, and source code is available at: this https URL

【23】 Neural Architectures for Biological Inter-Sentence Relation Extraction
标题：生物句间关系提取的神经结构
链接：https://arxiv.org/abs/2112.09288
作者：Enrique Noriega-Atala,Peter M. Lovett,Clayton T. Morrison,Mihai Surdeanu
机构：The University of Arizona, Tucson, AZ, USA
备注：Accepted at the Scientific Document Understanding workshop at AAAI'22

【24】 Link-Intensive Alignment for Incomplete Knowledge Graphs
标题：不完备知识图的链接密集对齐
链接：https://arxiv.org/abs/2112.09266
作者：Vinh Van Tong,Thanh Trung Huynh,Thanh Tam Nguyen,Hongzhi Yin,Quoc Viet Hung Nguyen,Quyet Thang Huynh
机构：Hanoi University of Science and Technology, Vietnam, Griffith University, Australia, The University of Queensland, Australia

【25】 Confidence-Aware Subject-to-Subject Transfer Learning for Brain-Computer Interface
标题：脑-机接口的可信度感知的主体间迁移学习
链接：https://arxiv.org/abs/2112.09243
作者：Dong-Kyun Han,Serkan Musellim,Dong-Young Kim
机构：Dept. Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea, Dept. Artificial Intelligence
备注：Submitted to 2022 10th IEEE International Winter Conference on Brain-Computer Interface

【26】 Two-view Graph Neural Networks for Knowledge Graph Completion
标题：用于知识图补全的双视图图神经网络
链接：https://arxiv.org/abs/2112.09231
作者：Vinh Tong,Dai Quoc Nguyen,Dinh Phung,Dat Quoc Nguyen
机构：VinAI Research, Vietnam; ,Oracle Labs, Australia; ,Monash University, Australia

【27】 Sim2Real Docs: Domain Randomization for Documents in Natural Scenes using Ray-traced Rendering
标题：Sim2Real Docs：基于光线跟踪渲染的自然场景中文档的域随机化
链接：https://arxiv.org/abs/2112.09220
作者：Nikhil Maddikunta,Huijun Zhao,Sumit Keswani,Alfy Samuel,Fu-Ming Guo,Nishan Srishankar,Vishwa Pardeshi,Austin Huang
机构：Fidelity Investments, Artificial Intelligence Center of Excellence
备注：Accepted to Neurips 2021 Data Centric AI (DCAI) Workshop

【28】 Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction
标题：用于细粒度特征提取的双曲解缠表示法
链接：https://arxiv.org/abs/2112.09215
作者：Chang-You Tai,Ming-Yao Li,Lun-Wei Ku
机构：Academia Sinica, Taipei, Taiwan

【29】 Semantic-Based Few-Shot Learning by Interactive Psychometric Testing
标题：基于语义的交互式心理测量学习
链接：https://arxiv.org/abs/2112.09201
作者：Lu Yin,Vlado Menkovski,Yulong Pei,Mykola Pechenizkiy
机构：Eindhoven University of Technology, Eindhoven , MB, Netherlands
备注：Accepted by AAAI 2022 Workshop on Interactive Machine Learning (IML@AAAI22)

【30】 Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes
标题：集成Taylor模型和Zonotope的神经网络控制系统验证
链接：https://arxiv.org/abs/2112.09197
作者：Christian Schilling,Marcelo Forets,Sebastian Guadalupe
机构： Aalborg University, Denmark, Universidad de la Rep´ublica, Uruguay
备注：accepted at AAAI-22

【31】 Causal Modeling With Infinitely Many Variables
标题：具有无限多个变量的因果模型
链接：https://arxiv.org/abs/2112.09171
作者：Spencer Peters,Joseph Y. Halpern
机构：Cornell University

【32】 On Optimizing Interventions in Shared Autonomy
标题：论共享自治中的优化干预
链接：https://arxiv.org/abs/2112.09169
作者：Weihao Tan,David Koleczek,Siddhant Pradhan,Nicholas Perello,Vivek Chettiar,Vishal Rohra,Aaslesha Rajaram,Soundararajan Srinivasan,H M Sajjad Hossain,Yash Chandak
机构： University of Massachusetts Amherst, Microsoft, MassMutual Data Science
备注：Accepted by AAAI2022

【33】 High Fidelity Visualization of What Your Self-Supervised Representation Knows About
标题：自我监督制图表达所知内容的高保真可视化
链接：https://arxiv.org/abs/2112.09164
作者：Florian Bordes,Randall Balestriero,Pascal Vincent
机构：Meta AI, Mila, Universite de Montreal, Canada CIFAR AI Chair

【34】 An Empirical Investigation of the Role of Pre-training in Lifelong Learning
标题：关于职前训练在终身学习中作用的实证研究
链接：https://arxiv.org/abs/2112.09153
作者：Sanket Vaibhav Mehta,Darshan Patil,Sarath Chandar,Emma Strubell
机构：Carnegie Mellon University,Mila - Quebec AI Institute,University of Montreal, École Polytechnique de Montréal,Canada CIFAR AI Chair
备注：30 pages

【35】 ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network
标题：ASC-Net：基于对抗性选择性切割网络的无监督医学异常分割
链接：https://arxiv.org/abs/2112.09135
作者：Raunak Dey,Wenbo Sun,Haibo Xu,Yi Hong
机构： Department of Computer Science, University of Georgia, Department of Radiology, Zhongnan Hospital of Wuhan University, Department of Computer Science and Engineering, Shanghai Jiao Tong University
备注：Currently in Submission to Medical Image Analysis Journal. Extension of DOI - 10.1007/978-3-030-87240-3_23 with more details and experiments and indepth analysis. arXiv admin note: substantial text overlap with arXiv:2103.03664

机器翻译，仅供参考

访问arxivdaily.com获取含摘要速递，更有收藏、搜索等功能，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域
同步公众号:arXiv每日学术速递，欢迎关注