机器学习学术速递[2021.7.7]

机器学习学术速递[2021.7.7]

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.LG 方向,今日共计110篇


Graph相关(图学习|图神经网络|图优化等)(7篇)

【1】 SAGE: Intrusion Alert-driven Attack Graph Extractor
标题:SAGE:入侵警报驱动的攻击图提取器
作者:Azqa Nadeem,Sicco Verwer,Stephen Moskal,Shanchieh Jay Yang
机构:Delft University of Technology, Delft, The Netherlands, Rochester Institute of Technology, Rochester, United States
备注:Accepted to appear in the 1st KDD Workshop on AI-enabled Cybersecurity Analytics (AI4cyber), 2021
链接arxiv.org/abs/2107.0278

【2】 Causal Bandits on General Graphs
标题:一般图上的因果图
作者:Aurghya Maiti,Vineet Nair,Gaurav Sinha
机构:Adobe Research, Technion Israel Institute of Technology
备注:35 pages
链接arxiv.org/abs/2107.0277

【3】 On Generalization of Graph Autoencoders with Adversarial Training
标题:关于对抗性训练的图形自动编码器的泛化
作者:Tianjin huang,Yulong Pei,Vlado Menkovski,Mykola Pechenizkiy
机构:Department of Mathematics and Computer Science, Eindhoven University of, Technology, MB Eindhoven, the Netherlands
备注:ECML 2021 Accepted
链接arxiv.org/abs/2107.0265

【4】 Multi-Level Graph Contrastive Learning
标题:多层次图对比学习
作者:Pengpeng Shao,Tong Liu,Dawei Zhang,Jianhua Tao,Feihu Che,Guohua Yang
机构:Yang, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China;
链接arxiv.org/abs/2107.0263

【5】 DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations
标题:DeepDDS:具有注意力机制的深度图神经网络预测协同药物组合
作者:J. Wang,X. Liu,S. Shen,L. Deng,H. Liu*
链接arxiv.org/abs/2107.0246

【6】 Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
标题:深图神经网络的Dirichlet能量约束学习
作者:Kaixiong Zhou,Xiao Huang,Daochen Zha,Rui Chen,Li Li,Soo-Hyun Choi,Xia Hu
机构:Texas A&M University, The Hong Kong Polytechnic University, Samsung Research America, Samsung Electronics
链接arxiv.org/abs/2107.0239

【7】 Physics-Informed Graph Learning for Robust Fault Location in Distribution Systems
标题:物理信息图学习在配电网鲁棒故障定位中的应用
作者:Wenting Li,Deepjyoti Deka
机构: weThe authors acknowledge the support from the Department of Energythrough the Advanced Grid Modeling (AGM) Program
备注:10 pages, 8 figures, journal
链接arxiv.org/abs/2107.0227

Transformer(3篇)

【1】 Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation
标题:利用空间变换网络进行自动大小和姿势同质化以改进和加速儿科分割
作者:Giammarco La Barbera,Pietro Gori,Haithem Boussaid,Bruno Belucci,Alessandro Delmonte,Jeanne Goulin,Sabine Sarnacki,Laurence Rouet,Isabelle Bloch
机构:- LTCI, Telecom Paris, Institut Polytechnique de Paris, France, - Philips Research Paris, Suresnes, France, - IMAG, Imagine Institute, Universite de Paris, France
备注:None
链接arxiv.org/abs/2107.0265

【2】 Long-Short Transformer: Efficient Transformers for Language and Vision
标题:长短Transformer:高效的语言和视觉转换器
作者:Chen Zhu,Wei Ping,Chaowei Xiao,Mohammad Shoeybi,Tom Goldstein,Anima Anandkumar,Bryan Catanzaro
机构:NVIDIA, University of Maryland, College Park
链接arxiv.org/abs/2107.0219

【3】 TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
标题:TransformerFusion:基于Transformer的单目RGB场景重建
作者:Aljaž Božič,Pablo Palafox,Justus Thies,Angela Dai,Matthias Nießner
机构:Technical University of Munich, Max Planck Institute for Intelligent Systems, Tübingen, Germany, aljazbozic.github.iotransformerfusion
备注:Video: this https URL
链接arxiv.org/abs/2107.0219

GAN|对抗|攻击|生成相关(5篇)

【1】 Semantic Segmentation Alternative Technique: Segmentation Domain Generation
标题:语义分割的替代技术:分割域生成
作者:Ana-Cristina Rogoz,Radu Muntean,Stefan Cobeli
机构:University of Bucharest, ETH Zürich, S, tefan Cobeli∗
备注:Accepted contribution at EEML2021 with poster presentation
链接arxiv.org/abs/2107.0252

【2】 DTGAN: Differential Private Training for Tabular GANs
标题:DTGAN:针对表格甘恩的差异化私人训练
作者:Aditya Kunar,Robert Birke,Lydia Chen,Zilong Zhao
机构:TU Delft, Delft, Netherlands, ABB Research Switzerland, D¨attwil, Switzerland, Lydia Y. Chen
备注:16 pages, 4 figures and 5 tables, submitted to the ACML 2021 conference
链接arxiv.org/abs/2107.0252

【3】 GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization
标题:GradDiv:基于梯度分集正则化的随机神经网络对抗鲁棒性
作者:Sungyoon Lee,Hoki Kim,Jaewook Lee
机构: Lee are with the Department of Industrial Engineering, Seoul National University
链接arxiv.org/abs/2107.0242

【4】 Improving Text-to-Image Synthesis Using Contrastive Learning
标题:利用对比学习改进文本到图像的合成
作者:Hui Ye,Xiulong Yang,Martin Takac,Rajshekhar Sunderraman,Shihao Ji
机构:Department of Computer Science, Georgia State University, Atlanta, GA, USA, Department of Industrial and Systems Engineering, Lehigh University, Bethlehem, PA, USA, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Masdar City, Abu Dhabi, UAE
链接arxiv.org/abs/2107.0242

【5】 Dueling Bandits with Adversarial Sleeping
标题:对抗性睡眠决斗土匪
作者:Aadirupa Saha,Pierre Gaillard
链接arxiv.org/abs/2107.0227

半/弱/无/有监督|不确定性|主动学习(8篇)

【1】 Depth-supervised NeRF: Fewer Views and Faster Training for Free
标题:深度监督NERF:免费提供更少的视图和更快的训练
作者:Kangle Deng,Andrew Liu,Jun-Yan Zhu,Deva Ramanan
机构:Carnegie Mellon University, Google, Argo AI, Sparse ,D Points, Depth-Supervised NeRF (Ours), Sparse views, Neural Radiance Fields (NeRF), Color Supervision for each pixel, Depth Supervision for each keypoint, Camera Parameters, +, Structure, From, Motion, : Rendered Depth
备注:Project page: this http URL GitHub: this https URL
链接arxiv.org/abs/2107.0279

【2】 Counterfactual Explanations in Sequential Decision Making Under Uncertainty
标题:不确定条件下序贯决策中的反事实解释
作者:Stratis Tsirtsis,Abir De,Manuel Gomez-Rodriguez
机构: and Manuel Gomez Rodriguez§§Max Planck Institute for Software Systems
备注:To appear at the ICML 2021 workshop on Interpretable Machine Learning in Healthcare
链接arxiv.org/abs/2107.0277

【3】 Evaluating subgroup disparity using epistemic uncertainty in mammography
标题:应用认知不确定性评估乳房X线摄影中的亚组差异
作者:Charles Lu,Andreanne Lemay,Katharina Hoebel,Jayashree Kalpathy-Cramer
备注:Accepted to the Interpretable Machine Learning in Healthcare workshop at the ICML 2021 conference
链接arxiv.org/abs/2107.0271

【4】 Enabling Un-/Semi-Supervised Machine Learning for MDSE of the Real-World CPS/IoT Applications
标题:为真实CPS/物联网应用的MDSE启用无/半监督机器学习
作者:Armin Moin,Atta Badii,Stephan Günnemann
机构:Department of Informatics, Technical University of Munich, Germany, Department of Computer Science, University of Reading, United Kingdom, Stephan G¨unnemann
备注:Preliminary version
链接arxiv.org/abs/2107.0269

【5】 Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4
标题:具有噪声学生模型和半监督损失函数的DCASE 2021挑战任务4的自我训练
作者:Nam Kyun Kim,Hong Kook Kim
机构:School of Electrical Engineering and Computer Science,AI Graduate School, Gwangju Institute of Science and Technology, Cheomdangwagi-ro, Gwangju , Republic of Korea
备注:5 pages, DCASE 2021 challenge Task 4 technical report
链接arxiv.org/abs/2107.0256

【6】 Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning
标题:鲁棒自监督深度强化学习的多模态互信息(MuMMI)训练
作者:Kaiqi Chen,Yong Lee,Harold Soh
机构:Dept. of Computer Science, National University of Singapore.
备注:10 pages, Published in ICRA 2021
链接arxiv.org/abs/2107.0233

【7】 Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
标题:当心你的异类!视觉答疑中离群点对主动学习的负面影响研究
作者:Siddharth Karamcheti,Ranjay Krishna,Li Fei-Fei,Christopher D. Manning
机构:Department of Computer Science, Stanford University
备注:Accepted at ACL-IJCNLP 2021. 17 pages, 16 Figures
链接arxiv.org/abs/2107.0233

【8】 End-to-End Weak Supervision
标题:端到端监管不力
作者:Salva Rühling Cachay,Benedikt Boecking,Artur Dubrawski
机构:Technical University of Darmstadt, Carnegie Mellon University
链接arxiv.org/abs/2107.0223

迁移|Zero/Few/One-Shot|自适应(6篇)

【1】 AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
标题:AdaRL:在迁移强化学习中适应什么、在哪里和如何适应
作者:Biwei Huang,Fan Feng,Chaochao Lu,Sara Magliacane,Kun Zhang
机构:Carnegie Mellon University, City University of Hong Kong, University of Cambridge, University of Amsterdam, MIT-IBM Watson AI Lab
链接arxiv.org/abs/2107.0272

【2】 VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
标题:VidLanKD:通过视频提炼知识传授提高语言理解能力
作者:Zineng Tang,Jaemin Cho,Hao Tan,Mohit Bansal
机构:UNC Chapel Hill
备注:18 pages (5 figures, 10 tables)
链接arxiv.org/abs/2107.0268

【3】 AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style
标题:AdaSpeech 3:自适应文本到语音转换,实现自然风格
作者:Yuzi Yan,Xu Tan,Bohan Li,Guangyan Zhang,Tao Qin,Sheng Zhao,Yuan Shen,Wei-Qiang Zhang,Tie-Yan Liu
机构:#Department of Electronic Engineering, Tsinghua University, China, $Microsoft Research Asia, China, %Microsoft Azure Speech, China, & Department of Electronic Engineering, The Chinese University of Hong Kong, China
备注:Accepted by INTERSPEECH 2021
链接arxiv.org/abs/2107.0253

【4】 Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition
标题:上下文特定神经序列到序列语音识别的即时一次单词学习
作者:Christian Huber,Juan Hussain,Sebastian Stüker,Alexander Waibel
机构:Interactive Systems Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany, Carnegie Mellon University, Pittsburgh PA, USA
备注:7 pages, 1 figure, 4 tables
链接arxiv.org/abs/2107.0226

【5】 Domain Adaptation via CycleGAN for Retina Segmentation in Optical Coherence Tomography
标题:基于CycleGAN的区域自适应光学相干层析视网膜分割
作者:Ricky Chen,Timothy T. Yu,Gavin Xu,Da Ma,Marinko V. Sarunic,Mirza Faisal Beg
机构:Simon Fraser University
备注:10 pages, 6 figures, 1 table
链接arxiv.org/abs/2107.0234

【6】 Near-optimal inference in adaptive linear regression
标题:自适应线性回归中的近优推断
作者:Koulik Khamaru,Yash Deshpande,Lester Mackey,Martin J. Wainwright
机构:Department of Statistics:, UC Berkeley, Department of Electrical Engineering and Computer Sciences‹, UC Berkeley, Voleon Group˚ and Microsoft Research;
备注:45 pages, 7 figures
链接arxiv.org/abs/2107.0226

强化学习(3篇)

【1】 Meta-Reinforcement Learning for Heuristic Planning
标题:启发式规划的元强化学习
作者:Ricardo Luna Gutierrez,Matteo Leonetti
机构:University of Leeds
备注:ICAPS 2021
链接arxiv.org/abs/2107.0260

【2】 Bayesian Nonparametric Modelling for Model-Free Reinforcement Learning in LTE-LAA and Wi-Fi Coexistence
标题:LTE-LAA和Wi-Fi共存中无模型强化学习的贝叶斯非参数建模
作者:Po-Kan Shih,Bahman Moraffah
机构:School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ
备注:arXiv admin note: substantial text overlap with arXiv:2105.12249
链接arxiv.org/abs/2107.0243

【3】 Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems
标题:倾听的代理:多感觉系统的高通量强化学习
作者:Shashank Hegde,Anssi Kanervisto,Aleksei Petrenko
机构:University of Southern California, Los Angeles, United States, University of Eastern Finland, Joensuu, Finland
备注:To appear in IEEE Conference on Games 2021. Video demonstrations and experiment can be found at this https URL
链接arxiv.org/abs/2107.0219

元学习(1篇)

【1】 Meta-learning Amidst Heterogeneity and Ambiguity
标题:异质与歧义中的元学习
作者:Kyeongryeol Go,Seyoung Yun
机构:Graduate School of AI, KAIST, Daejeon, South Korea
链接arxiv.org/abs/2107.0222

符号|符号学习(2篇)

【1】 Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning
标题:用双系统、神经-符号推理提高神经序列模型的一致性和一致性
作者:Maxwell Nye,Michael Henry Tessler,Joshua B. Tenenbaum,Brenden M. Lake
机构:MIT, NYU and Facebook AI Research
链接arxiv.org/abs/2107.0279

【2】 A comparison of LSTM and GRU networks for learning symbolic sequences
标题:学习符号序列的LSTM网络和GRU网络的比较
作者:Roberto Cahuantzi,Xinye Chen,Stefan Güttel
机构:The University of Manchester, Department of Mathematics, Manchester, M,PL, United Kingdom
备注:12 pages, 8 figures, submitted to the International Conference on Neural Information Processing 2021
链接arxiv.org/abs/2107.0224

医学相关(7篇)

【1】 Early Recognition of Ball Catching Success in Clinical Trials with RNN-Based Predictive Classification
标题:基于RNN的预测分类对临床试验接球成功的早期识别
作者:Jana Lang,Martin A. Giese,Matthis Synofzik,Winfried Ilg,Sebastian Otte
机构: Section for Computational Sensomotorics, Department of Cognitive Neurology, Centre for Integrative Neuroscience & Hertie Institute for Clinical Brain Research, Department of Neurodegeneration, Hertie Institute for Clinical Brain Research &
备注:Accepted by the 30th International Conference on Artificial Neural Networks (ICANN 2021)
链接arxiv.org/abs/2107.0244

【2】 SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging
标题:SplitAVG:一种异构性感知的医学成像联合深度学习方法
作者:Miao Zhang,Liangqiong Qu,Praveer Singh,Jayashree Kalpathy-Cramer,Daniel L. Rubin
链接arxiv.org/abs/2107.0237

【3】 Leveraging Clinical Context for User-Centered Explainability: A Diabetes Use Case
标题:利用临床环境实现以用户为中心的可理解性:糖尿病使用案例
作者:Shruthi Chari,Prithwish Chakraborty,Mohamed Ghalwash,Oshani Seneviratne,Elif K. Eyigoz,Daniel M. Gruen,Ching-Hua Chen,Pablo Meyer Rojas,Deborah L. McGuinness
机构: Rensselaer Polytechnic Institute (RPI), NY, USA, Center for Computational Health, IBM Research, NY, USA, IBM Watson Health, MA, USA
备注:4 pages, 4 tables, 3 figures, 2.5 pages appendices To appear and accepted at: KDD Workshop on Applied Data Science for Healthcare (DSHealth), 2021, Virtual
链接arxiv.org/abs/2107.0235

【4】 DeepCEL0 for 2D Single Molecule Localization in Fluorescence Microscopy
标题:用于荧光显微镜二维单分子定位的DeepCEL0
作者:Pasquale Cascarano,Maria Colomba Comes,Andrea Sebastiani,Arianna Mencattini,Elena Loli Piccolomini,Eugenio Martinelli
机构:Department of Mathematics, University of Bologna, Bologna, Italy, Department of Electronic Engineering, University of Tor Vergata, Rome, Italy, Department of Computer Science and Engineering
链接arxiv.org/abs/2107.0228

【5】 Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-specific Atlas Maps
标题:应用疾病特异性图谱检测胎儿超声左心发育不良综合征
作者:Samuel Budd,Matthew Sinclair,Thomas Day,Athanasios Vlontzos,Jeremy Tan,Tianrui Liu,Jaqueline Matthew,Emily Skelton,John Simpson,Reza Razavi,Ben Glocker,Daniel Rueckert,Emma C. Robinson,Bernhard Kainz
机构: Imperial College London, Dept. Computing, BioMedIA, London, UK, King’s College London, London, UK, Guy’s and St Thomas’ NHS Foundation Trust, London, UK, School of Health Sciences, City, University of London, London, UK
备注:MICCAI'21 Main Conference
链接arxiv.org/abs/2107.0264

【6】 Differentially private federated deep learning for multi-site medical image segmentation
标题:差分私有联合深度学习在多点医学图像分割中的应用
作者:Alexander Ziller,Dmitrii Usynin,Nicolas Remerscheid,Moritz Knolle,Marcus Makowski,Rickmer Braren,Daniel Rueckert,Georgios Kaissis
机构:Institute for Artificial Intelligence and Informatics in Medicine, Technical University of Munich, Munich, Germany, Institute of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany, OpenMined
备注:Submitted to the Journal of Machine Learning in Biomedical Imaging (MELBA)
链接arxiv.org/abs/2107.0258

【7】 WisdomNet: Prognosis of COVID-19 with Slender Prospect of False Negative Cases and Vaticinating the Probability of Maturation to ARDS using Posteroanterior Chest X-Rays
标题:WisdomNet:冠状病毒的预后与假阴性病例前景渺茫及应用后前胸X线片评估ARDS的成熟概率
作者:Peeyush Kumar,Ayushe Gangal,Sunita Kumari
机构:G.B. Pant Government Engineering College, Delhi - , India.
备注:None
链接arxiv.org/abs/2107.0139

蒸馏|知识提取(1篇)

【1】 CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
标题:CORRED:利用蒸馏的连续表示推广虚假媒体检测
作者:Minha Kim,Shahroz Tariq,Simon S. Woo
机构:College of Computing and Informatics, Sungkyunkwan University, South Korea, Department of Applied Data Science, Time, TASK N, DF, F,F, FS, NT, Task , (e.g., PGGAN), Task , (e.g., StarGAN), Task , (e.g., StyleGAN), Task , (e.g., FaceSwap), Task , (e.g., Face,Face)
备注:10 pages, 2 Figures, 10 Tables, Accepted for publication in the 29th ACM International Conference on Multimedia (ACMMM '21)
链接arxiv.org/abs/2107.0240

聚类(3篇)

【1】 Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering
标题:端到端深度聚类的期望最大化神经混合模型
作者:Dumindu Tissera,Kasun Vithanage,Rukshan Wijesinghe,Alex Xavier,Sanath Jayasena,Subha Fernando,Ranga Rodrigo
机构:Department of Electronic & Telecommunication Engineering, Univerisity of Moratuwa, Sri Lanka, CodeGen QBITS Lab, University of Moratuwa, Sri Lanka
链接arxiv.org/abs/2107.0245

【2】 Deep Visual Attention-Based Transfer Clustering
标题:基于深度视觉注意的转移聚类
作者:Akshaykumar Gunari,Shashidhar Veerappa Kudari,Sukanya Nadagadalli,Keerthi Goudnaik,Ramesh Ashok Tabib,Uma Mudenagudi,Adarsh Jamadandi
机构:Jamadandi, KLE Technological University, Hubballi, India
链接arxiv.org/abs/2107.0241

【3】 Clustering Structure of Microstructure Measures
标题:微观结构测度的聚类结构
作者:Liao Zhu,Ningning Sun,Martin T. Wells
机构: Cornell University, ‡Department of Computer Science
链接arxiv.org/abs/2107.0228

自动驾驶|车辆|车道检测等(1篇)

【1】 Effects of Smart Traffic Signal Control on Air Quality
标题:智能交通信号控制对空气质量的影响
作者:Paolo Fazzini,Marco Torre,Valeria Rizza,Francesco Petracchini
机构:Petracchini, Institute of Atmospheric Pollution Research, CNR, Rome, Italy
备注:23 pages, 21 figures. arXiv admin note: substantial text overlap with arXiv:2107.01347
链接arxiv.org/abs/2107.0236

点云|SLAM|雷达|激光|深度RGBD相关(1篇)

【1】 A deep-learning--based multimodal depth-aware dynamic hand gesture recognition system
标题:基于深度学习的多模态深度感知动态手势识别系统
作者:Hasan Mahmud,Mashrur Mahmud Morshed,Md. Kamrul Hasan
机构:Systems and Software Lab (SSL), Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur, Dhaka, Bangladesh
链接arxiv.org/abs/2107.0254

联邦学习|隐私保护|加密(1篇)

【1】 FedFog: Network-Aware Optimization of Federated Learning over Wireless Fog-Cloud Systems
标题:FedFog:无线雾云系统联合学习的网络感知优化
作者:Van-Dinh Nguyen,Symeon Chatzinotas,Bjorn Ottersten,Trung Q. Duong
备注:30 pages, 12 figures. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
链接arxiv.org/abs/2107.0275

推理|分析|理解|解释(4篇)

【1】 Physics-informed regularization and structure preservation for learning stable reduced models from data with operator inference
标题:基于物理信息正则化和结构保持的算子推理数据学习稳定约简模型
作者:Nihar Sawant,Boris Kramer,Benjamin Peherstorfer
机构:Courant Institute of Mathematical Sciences, New York University†Department of Mechanical and Aerospace Engineering, University of California
链接arxiv.org/abs/2107.0259

【2】 CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
标题:CAP-RAM:一种用于精确可编程CNN推理的电荷域内存计算6T-SRAM
作者:Zhiyu Chen,Zhanghao Yu,Qing Jin,Yan He,Jingyu Wang,Sheng Lin,Dai Li,Yanzhi Wang,Kaiyuan Yang
机构: Senior Member, IEEE
备注:None
链接arxiv.org/abs/2107.0238

【3】 A Review of Explainable Artificial Intelligence in Manufacturing
标题:制造业中的可解释人工智能研究综述
作者:Georgios Sofianidis,Jože M. Rožanec,Dunja Mladenić,Dimosthenis Kyriazis
机构: Department of Digital Systems, University of Piraeus, Piraeus, Greece, Joˇzef Stefan Institute, Jamova , Ljubljana, Slovenia, Joˇzef Stefan International Postgraduate School, Jamova , Ljubljana, Slovenia
链接arxiv.org/abs/2107.0229

【4】 Causal Inference with Corrupted Data: Measurement Error, Missing Values, Discretization, and Differential Privacy
标题:损坏数据的因果推断:测量误差、缺失值、离散化和差分隐私
作者:Anish Agarwal,Rahul Singh
机构:MIT
备注:99 pages
链接arxiv.org/abs/2107.0278

检测相关(1篇)

【1】 Sarcasm Detection: A Comparative Study
标题:反讽检测:一种比较研究
作者:Hamed Yaghoobian,Hamid R. Arabnia,Khaled Rasheed
机构:Department of Computer Science, University of Georgia, Athens, GA, USA
链接arxiv.org/abs/2107.0227

分类|识别(3篇)

【1】 Dynamical System Parameter Identification using Deep Recurrent Cell Networks
标题:基于深递归细胞网络的动态系统参数辨识
作者:Erdem Akagündüz,Oguzhan Cifdaloz
备注:Final version published in Journal of Neural Computing and Applications
链接arxiv.org/abs/2107.0242

【2】 Vision Xformers: Efficient Attention for Image Classification
标题:视觉变形器:图像分类的有效关注点
作者:Pranav Jeevan,Amit Sethi
机构:Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India
备注:7 pages, 4 figures
链接arxiv.org/abs/2107.0223

【3】 Morphological Classification of Galaxies in S-PLUS using an Ensemble of Convolutional Networks
标题:基于卷积网络系综的S-plus星系形态分类
作者:N. M. Cardoso,G. B. O. Schwarz,L. O. Dias,C. R. Bom,L. Sodré Jr.,C. Mendes de Oliveira
机构:Escola Polit´ecnica, Universidade de S˜ao Paulo, Av. Prof. Luciano Gualberto, Butant˜a, S˜ao Paulo – SP, CEP ,-, Brasil, Universidade Presbiteriana Mackenzie, Rua da Consolac¸˜ao, Consolac¸˜ao, S˜ao Paulo – SP, CEP ,-, Brasil
备注:18 pages, 13 figures, codes and data available at this https URL, text in portuguese
链接arxiv.org/abs/2107.0228

表征(1篇)

【1】 Equivariant bifurcation, quadratic equivariants, and symmetry breaking for the standard representation of $S_n$
标题:$S_n$标准表示的等变分岔、二次等变和对称破缺
作者:Yossi Arjevani,Michael Field
链接arxiv.org/abs/2107.0242

编码器(2篇)

【1】 Rethinking Positional Encoding
标题:对位置编码的再思考
作者:Jianqiao Zheng,Sameera Ramasinghe,Simon Lucey
机构:University of Adelaide
链接arxiv.org/abs/2107.0256

【2】 InfoNCE is a variational autoencoder
标题:InfoNCE是一个变分自动编码器
作者:Laurence Aitchison
机构:Department of Computer Science, University of Bristol, Bristol, UK
链接arxiv.org/abs/2107.0249

优化|敛散性(1篇)

【1】 Deep Learning Methods for Joint Optimization of Beamforming and Fronthaul Quantization in Cloud Radio Access Networks
标题:云无线接入网波束形成和波前量化联合优化的深度学习方法
作者:Daesung Yu,Hoon Lee,Seok-Hwan Park,Seung-Eun Hong
机构: Lee is with the Department of Information and Communications Engineering, Pukyong National University
备注:accepted for publication on IEEE Wireless Communications Letters
链接arxiv.org/abs/2107.0252

预测|估计(9篇)

【1】 DEANN: Speeding up Kernel-Density Estimation using Approximate Nearest Neighbor Search
标题:Deann:利用近似最近邻搜索加速核密度估计
作者:Matti Karppa,Martin Aumüller,Rasmus Pagh
机构:IT University of Copenhagen, BARC
备注:24 pages, 1 figure. Submitted for review
链接arxiv.org/abs/2107.0273

【2】 Remote sensing, AI and innovative prediction methods for adapting cities to the impacts of the climate change
标题:遥感、人工智能和城市适应气候变化影响的创新预测方法
作者:Beril Sirmacek
机构:Smart Cities, School of Creative Technology, KEY WORDS: Climate Change, Global Warming, Remote Sensing, Artificial Intelligence, Predictive Modeling, Smart Cities, Sustainable Development Goals (SDGs)
链接arxiv.org/abs/2107.0269

【3】 An Evaluation of Machine Learning and Deep Learning Models for Drought Prediction using Weather Data
标题:基于天气数据的机器学习和深度学习模型在干旱预测中的评价
作者:Weiwei Jiang,Jiayun Luo
机构:Department of Electronic Engineering, Tsinghua University, Beijing, China, Department of Statistics, University of California-Los Angeles, Los Angeles, USA
备注:Github link: this https URL
链接arxiv.org/abs/2107.0251

【4】 Learning an Explicit Hyperparameter Prediction Policy Conditioned on Tasks
标题:学习以任务为条件的显式超参数预测策略
作者:Jun Shu,Deyu Meng,Zongben Xu
机构:School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and, Network Security, Xi’an Jiaotong University, Xi’an, Shaan’xi Province, P. R. China, Pazhou Lab, Guangzhou, Guangdong Province, P. R. China, Editor:
备注:59 pages
链接arxiv.org/abs/2107.0237

【5】 Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
标题:有效的一阶上下文环:预测、分配和三角判别
作者:Dylan J. Foster,Akshay Krishnamurthy
机构:Microsoft Research, New England, Microsoft Research, NYC
链接arxiv.org/abs/2107.0223

【6】 Featurized Density Ratio Estimation
标题:特征密度比估计
作者:Kristy Choi,Madeline Liao,Stefano Ermon
机构:Computer Science Department, Stanford University
备注:First two authors contributed equally
链接arxiv.org/abs/2107.0221

【7】 Midwifery Learning and Forecasting: Predicting Content Demand with User-Generated Logs
标题:助产学习和预测:使用用户生成的日志预测内容需求
作者:Anna Guitart,Ana Fernández del Río,África Periáñez
机构:benshi.ai, Barcelona, Spain, Lauren Bellhouse, Maternity Foundation, Copenhagen, Denmark
链接arxiv.org/abs/2107.0248

【8】 Total Nitrogen Estimation in Agricultural Soils via Aerial Multispectral Imaging and LIBS
标题:基于航空多光谱成像和LIBS的农业土壤全氮估算
作者:Md Abir Hossen,Prasoon K Diwaka,Shankarachary Ragi
机构: satellite-based sensing OPEN 1Department of Electrical Engineering, South Dakota School of Mines and Technology, 2Department of Mechanical Engineering
备注:None
链接arxiv.org/abs/2107.0235

【9】 Automated age-related macular degeneration area estimation -- first results
标题:自动估计年龄相关性黄斑变性面积--第一个结果
作者:Rokas Pečiulis,Mantas Lukoševičius,Algimantas Kriščiukaitis,Robertas Petrolis,Dovilė Buteikienė
机构:Dovil˙e Buteikien˙e, Kaunas University of Technology, Kaunas, Lithuania, Department of Physics, Mathematics and Biophysics, Lithuanian University, Department of Ophthalmology, Mathematics and Biophysics, Lithuanian, University of Health Sciences
链接arxiv.org/abs/2107.0221

其他神经网络|深度学习|模型|建模(23篇)

【1】 Data-driven reduced order modeling of environmental hydrodynamics using deep autoencoders and neural ODEs
标题:使用深度自动编码器和神经ODE的环境流体力学数据驱动降阶建模
作者:Sourav Dutta,Peter Rivera-Casillas,Orie M. Cecil,Matthew W. Farthing,Emma Perracchione,Mario Putti
机构: USACE Engineer Research Development Center, Halls Ferry Rd, Vicksburg MS , USA, University of Genoa, Via Dodecaneso , Genova, Italy, University of Padua, Via Trieste, Padova, Italy
备注:16 pages, 7 figures, To Appear in the proceedings of the IXth International Conference on Computational Methods for Coupled Problems in Science and Engineering (COUPLED PROBLEMS 2021), 14-16 June, 2021. arXiv admin note: substantial text overlap with arXiv:2104.13962
链接arxiv.org/abs/2107.0278

【2】 Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network
标题:锯齿形阶乘主题嵌入引导的Gamma信任网络
作者:Zhibin Duan,Dongsheng Wang,Bo Chen,Chaojie Wang,Wenchao Chen,Yewen Li,Jie Ren,Mingyuan Zhou
机构: have the ability to discover the underly-Equal contribution 1National Laboratory of Radar Sig-nal Processing, Xidian University, 2McCombsSchool of Business The University of Texas at Austin
链接arxiv.org/abs/2107.0275

【3】 Provable Lipschitz Certification for Generative Models
标题:生成模型的可证明Lipschitz证明
作者:Matt Jordan,Alexandros G. Dimakis
机构:We present a general algorithm for mapping zonotopes 1University of Texas at Austin
备注:Accepted into ICML 2021
链接arxiv.org/abs/2107.0273

【4】 ML-Quadrat & DriotData: A Model-Driven Engineering Tool and a Low-Code Platform for Smart IoT Services
标题:ML-Quadrat&DriotData:模型驱动的工程工具和智能物联网服务的低代码平台
作者:Armin Moin,Andrei Mituca,Atta Badii,Stephan Günnemann
机构:Department of Informatics, Technical University of Munich, Germany, DriotData UG, Department of Computer Science, University of Reading, United Kingdom
备注:Preliminary version
链接arxiv.org/abs/2107.0269

【5】 A Model-Driven Engineering Approach to Machine Learning and Software Modeling
标题:一种模型驱动的机器学习和软件建模工程方法
作者:Armin Moin,Atta Badii,Stephan Günnemann
机构:G¨unnemann, Received: date Accepted: date
备注:Preliminary version
链接arxiv.org/abs/2107.0268

【6】 Does Dataset Complexity Matters for Model Explainers?
标题:数据集复杂性对模型解释器重要吗?
作者:José Ribeiro,Raíssa Silva,Ronnie Alves
机构: Federal University of Par´a - UFPA, Bel´em, Brazil, Federal Institute of Par´a - IFPA, Ananindeua, Brazil, IRMB, Montpellier University, Montpellier, France, La Ligue Contre le Cancer, Montpellier, France
备注:12 pages, 5 figures
链接arxiv.org/abs/2107.0266

【7】 A Multi-Objective Approach for Sustainable Generative Audio Models
标题:一种可持续生成音频模型的多目标方法
作者:Constance Douwes,Philippe Esling,Jean-Pierre Briot
机构:IRCAM, Sorbonne Université, CNRS, UMR , F-, Paris, France, Sorbonne Université, CNRS, LIP, F-, Paris, France, UNIRIO, Rio de Janeiro, RJ ,-, Brazil
备注:9 pages, 3 figures
链接arxiv.org/abs/2107.0262

【8】 Prioritized training on points that are learnable, worth learning, and not yet learned
标题:对可学、值得学和尚未学到的要点进行优先训练
作者:Sören Mindermann,Muhammed Razzak,Winnie Xu,Andreas Kirsch,Mrinank Sharma,Adrien Morisot,Aidan N. Gomez,Sebastian Farquhar,Jan Brauner,Yarin Gal
机构: University of Oxford, UnitedKingdom 2Department of Computer Science, University ofToronto, Canada 3Cohere 4Department of Statistics, Universityof Oxford
备注:None
链接arxiv.org/abs/2107.0256

【9】 The QR decomposition for radial neural networks
标题:径向神经网络的QR分解
作者:Iordan Ganev,Robin Walters
备注:30 pages
链接arxiv.org/abs/2107.0255

【10】 Shell Language Processing: Unix command parsing for Machine Learning
标题:外壳语言处理:机器学习的Unix命令解析
作者:Dmitrijs Trizna
机构:Department of Computer Science, University of Helsinki
备注:3 pages, 1 figure, 1 table
链接arxiv.org/abs/2107.0243

【11】 Deep Network Approximation With Accuracy Independent of Number of Neurons
标题:精度与神经元数目无关的深度网络逼近
作者:Zuowei Shen,Haizhao Yang,Shijun Zhang
机构:‡Department of Mathematics, Purdue University (haizhao, §Department of Mathematics, National University of Singapore (zhangshijun
链接arxiv.org/abs/2107.0239

【12】 Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networks
标题:片上互连对深度神经网络内存加速的影响
作者:Gokul Krishnan,Sumit K. Mandal,Chaitali Chakrabarti,Jae-sun Seo,Umit Y. Ogras,Yu Cao
机构: Arizona State University, University of Wisconsin-Madison
链接arxiv.org/abs/2107.0235

【13】 Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections
标题:作为交流的物理交互:从人类矫正中在线学习机器人目标
作者:Dylan P. Losey,Andrea Bajcsy,Marcia K. O'Malley,Anca D. Dragan
机构:edu 2University of California, edu 3Rice University; omalleym, Department of Mechanical Engineering
链接arxiv.org/abs/2107.0234

【14】 Memory-Sample Lower Bounds for Learning Parity with Noise
标题:带噪声学习奇偶校验的记忆样本下界
作者:Sumegha Garg,Pravesh K. Kothari,Pengda Liu,Ran Raz
机构: Department of Computer Science, Carnegie Mellon University, Stanford University
备注:19 pages. To appear in RANDOM 2021. arXiv admin note: substantial text overlap with arXiv:1708.02639
链接arxiv.org/abs/2107.0232

【15】 Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity
标题:连通性问题:通过有效稀疏性的镜头修剪神经网络
作者:Artem Vysogorets,Julia Kempe
机构:New York University, Center for Data Science and, Department of Computer Science, Courant Institute
链接arxiv.org/abs/2107.0230

【16】 "Garbage In, Garbage Out" Revisited: What Do Machine Learning Application Papers Report About Human-Labeled Training Data?
作者:R. Stuart Geiger,Dominique Cope,Jamie Ip,Marsha Lotosh,Aayush Shah,Jenny Weng,Rebekah Tang
机构:†, Aayush, For correspondence:, †The majority of the work on this, paper was conducted when this, author was affiliated with the, University of California, Berkeley., DOI: doi.org,.,qss_a_, Data, code, and protocols:, doi.org,.,zenodo., Peer reviews:
备注:None
链接arxiv.org/abs/2107.0227

【17】 Generalization by design: Shortcuts to Generalization in Deep Learning
标题:设计概括:深度学习中概括的捷径
作者:Petr Taborsky,Lars Kai Hansen
机构:Technical University of Denmark, Department of Applied Mathematics and Computer Science, Richard Petersens Plads, Kgs. Lyngby, Denmark
备注:16 pages + 9 pages supplementary
链接arxiv.org/abs/2107.0225

【18】 Label noise in segmentation networks : mitigation must deal with bias
标题:分段网络中的标签噪声:缓解必须处理偏差
作者:Eugene Vorontsov,Samuel Kadoury
机构:´Ecole Polytechnique de Montr´eal, Montr´eal QC H,T,J, Canada
链接arxiv.org/abs/2107.0218

【19】 Quantum Annealing Formulation for Binary Neural Networks
标题:二元神经网络的量子退火公式
作者:Michele Sasdelli,Tat-Jun Chin
机构:School of Computer Science, The University of Adelaide, Adelaide SA , Australia
备注:13 pages, 4 figures
链接arxiv.org/abs/2107.0275

【20】 A new smart-cropping pipeline for prostate segmentation using deep learning networks
标题:一种新的基于深度学习网络的智能切割前列腺分割流水线
作者:Dimitrios G. Zaridis,Eugenia Mylona,Kostas Marias,Nikolaos Papanikolaou,Nikolaos S. Tachos,Dimitrios I. Fotiadis
机构:A new smart-cropping pipeline for prostate, segmentation using deep learning networks,
备注:8 pages, 6 figures, 1 table
链接arxiv.org/abs/2107.0247

【21】 Asymptotics of Network Embeddings Learned via Subsampling
标题:通过次抽样学习的网络嵌入的渐近性
作者:Andrew Davison,Morgane Austern
机构:Department of Statistics, Columbia University, New York, NY ,-, USA, Harvard University, Cambridge, MA ,-, USA
备注:98 pages, 3 figures, 1 table
链接arxiv.org/abs/2107.0236

【22】 Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology
标题:细胞类型直方图:自动骨髓细胞学的深度学习
作者:Rohollah Moosavi Tayebi,Youqing Mu,Taher Dehkharghanian,Catherine Ross,Monalisa Sur,Ronan Foley,Hamid R. Tizhoosh,Clinton JV Campbell
机构:McMaster University, Hamilton, Canada, Kimia Lab, University of Waterloo, Waterloo, Canada, Juravinski Hospital and Cancer Centre, Hamilton, Canada
链接arxiv.org/abs/2107.0229

【23】 A Deep Learning-Based Particle-in-Cell Method for Plasma Simulations
标题:一种基于深度学习的等离子体粒子单元模拟方法
作者:Xavier Aguilar,Stefano Markidis
机构:Electrical Engineering and Computer Science School, KTH Royal Institute of Technology, Stockholm, Sweden
备注:Submitted to AI4S Workshop at Cluster Conference
链接arxiv.org/abs/2107.0223

其他(17篇)

【1】 Learned Visual Navigation for Under-Canopy Agricultural Robots
标题:学习的冠下农业机器人视觉导航
作者:Arun Narenthiran Sivakumar,Sahil Modi,Mateus Valverde Gasparino,Che Ellis,Andres Eduardo Baquero Velasquez,Girish Chowdhary,Saurabh Gupta
机构:Department of Agricultural and Biological Engineering, University of Illinois at Urbana-Champaign (UIUC), Department of Computer Science, UIUC,Department of Electrical and Computer Engineering, UIUC, EarthSense Inc.
备注:RSS 2021. Project website with data and videos: this https URL
链接arxiv.org/abs/2107.0279

【2】 Neural Computing
标题:神经计算
作者:Ayushe Gangal,Peeyush Kumar,Sunita Kumari,Aditya Kumar
机构: Deenbandhu Chhotu Ram University Of Science And Technology 2 ayushe 17
备注:Book chapter, 25 pages, 16 figures, 5 tables
链接arxiv.org/abs/2107.0274

【3】 Dueling Bandits with Team Comparisons
标题:用团队比较法决斗土匪
作者:Lee Cohen,Ulrike Schmidt-Kraepelin,Yishay Mansour
机构: 1 Blavatnik School of Computer Science, Tel Aviv University, Technische Universität Berlin
链接arxiv.org/abs/2107.0273

【4】 A Unified Off-Policy Evaluation Approach for General Value Function
标题:一般价值函数的统一非政策性评价方法
作者:Tengyu Xu,Zhuoran Yang,Zhaoran Wang,Yingbin Liang
机构:The Ohio State University, Princeton University, Northwestern University
备注:submitted for publication
链接arxiv.org/abs/2107.0271

【5】 Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
标题:基于改进的深度图像先验和残差重建的高光谱全息锐化
作者:Wele Gedara Chaminda Bandara,Jeya Maria Jose Valanarasu,Vishal M. Patel
机构: Patel are with Whiting School of Engineering, The Johns HopkinsUniversity
链接arxiv.org/abs/2107.0263

【6】 Intrinsic uncertainties and where to find them
标题:内在不确定性及其在哪里找到
作者:Francesco Farina,Lawrence Phillips,Nicola J Richmond
备注:Presented at the ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning
链接arxiv.org/abs/2107.0252

【7】 EVARS-GPR: EVent-triggered Augmented Refitting of Gaussian Process Regression for Seasonal Data
标题:EVARS-GPR:季节性数据高斯过程回归的事件触发增广修正
作者:Florian Haselbeck,Dominik G. Grimm
机构: Technical University of Munich, TUM Campus Straubing for Biotechnology and, Sustainability, Bioinformatics, Schulgasse , Straubing, Germany, Weihenstephan-Triesdorf University of Applied Sciences, Bioinformatics, Petersgasse , Straubing, Germany
链接arxiv.org/abs/2107.0246

【8】 Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
标题:使用自动嵌入级联增强的通用依赖项解析
作者:Xinyu Wang,Zixia Jia,Yong Jiang,Kewei Tu
机构:⋄School of Information Science and Technology, ShanghaiTech University, Shanghai Engineering Research Center of Intelligent Vision and Imaging, †DAMO Academy, Alibaba Group
备注:Second Place in IWPT 2021 shared task, 7 pages
链接arxiv.org/abs/2107.0241

【9】 An Inverse QSAR Method Based on Linear Regression and Integer Programming
标题:一种基于线性回归和整数规划的反QSAR方法
作者:Jianshen Zhu,Naveed Ahmed Azam,Kazuya Haraguchi,Liang Zhao,Hiroshi Nagamochi,Tatsuya Akutsu
机构:. Department of Applied Mathematics and Physics, Kyoto University, Kyoto ,-, Japan, . Graduate School of Advanced Integrated Studies in Human Survavibility (Shishu-Kan), Kyoto Univer-
链接arxiv.org/abs/2107.0238

【10】 A Short Note on the Relationship of Information Gain and Eluder Dimension
标题:关于信息增益与Eluder维数关系的一点注记
作者:Kaixuan Huang,Sham M. Kakade,Jason D. Lee,Qi Lei
机构:Princeton University, University of Washington, Microsoft Research
链接arxiv.org/abs/2107.0237

【11】 Weighted Gaussian Process Bandits for Non-stationary Environments
标题:非平稳环境下的加权高斯过程带
作者:Yuntian Deng,Xingyu Zhou,Baekjin Kim,Ambuj Tewari,Abhishek Gupta,Ness Shroff
机构:Ohio State University, Columbus, OH, USA, Wayne State University, Detroit, MI, USA, Department of Statistics, University of Michigan, Ann Arbor, MI, USA, Department of ECE and CSE
链接arxiv.org/abs/2107.0237

【12】 Discrete-Valued Neural Communication
标题:离散值神经通信
作者:Dianbo Liu Dianbo_Liu,Alex Lamb,Kenji Kawaguchi,Anirudh Goyal,Chen Sun,Michael Curtis Mozer,Yoshua Bengio
机构:MIT, MILA and Deepmind, Google Brain and University of Colorado, co-first author
链接arxiv.org/abs/2107.0236

【13】 An Ensemble Noise-Robust K-fold Cross-Validation Selection Method for Noisy Labels
标题:一种适用于含噪标签的集成抗噪K-折叠交叉验证选择方法
作者:Yong Wen,Marcus Kalander,Chanfei Su,Lujia Pan
机构:Noah’s Ark Lab, Huawei Technologies
备注:Accepted by the IJCAI2021 Weakly Supervised Representation Learning (WSRL) Workshop
链接arxiv.org/abs/2107.0234

【14】 Energy and Thermal-aware Resource Management of Cloud Data Centres: A Taxonomy and Future Directions
标题:云数据中心的能源和热感知资源管理:分类和未来方向
作者:Shashikant Ilager,Rajkumar Buyya
机构:University of Melbourne, Australia
备注:Submitted to ACM Computing Surveys
链接arxiv.org/abs/2107.0234

【15】 A visual introduction to Gaussian Belief Propagation
标题:高斯信念传播的可视化介绍
作者:Joseph Ortiz,Talfan Evans,Andrew J. Davison
机构:Imperial College London,DeepMind
备注:See online version of this article: this https URL
链接arxiv.org/abs/2107.0230

【16】 VolNet: Estimating Human Body Part Volumes from a Single RGB Image
标题:VolNet:从单个RGB图像估计人体部位体积
作者:Fabian Leinen,Vittorio Cozzolino,Torsten Schön
机构:Technical University of Munich, Audi AG, Torsten Sch¨on, Technische Hochschule, Ingolstadt
链接arxiv.org/abs/2107.0225

【17】 Implicit Variational Conditional Sampling with Normalizing Flows
标题:带归一化流的隐式变分条件抽样
作者:Vincent Moens,Aivar Sootla,Haitham Bou Ammar,Jun Wang
机构:Huawei R&D UK, University College London
链接arxiv.org/abs/2107.0247

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
发布于 2021-07-07 09:59