同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)
cs.LG 方向,今日共计66篇
[cs.LG]:
【1】 HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
标题:HUGE2:一个用于边缘计算的高度解缠的生成模型引擎
作者: Feng Shi, Song-Chun Zhu
链接:https://arxiv.org/abs/1907.11210
【2】 Prediction of Highway Lane Changes Based on Prototype Trajectories
标题:基于原型轨迹的公路车道变化预测
作者: David Augustin, Ulrich Konigorski
备注:VDI AUTOREG 2019, 17 pages, 5 figures
链接:https://arxiv.org/abs/1907.11208
【3】 Unsupervised Domain Adaptation via Calibrating Uncertainties
标题:通过校准不确定性的无监督域自适应
作者: Ligong Han, Dimitris Metaxas
链接:https://arxiv.org/abs/1907.11202
【4】 Google Research Football: A Novel Reinforcement Learning Environment
标题:Google Research Football:一种新的强化学习环境
作者: Karol Kurach, Sylvain Gelly
链接:https://arxiv.org/abs/1907.11180
【5】 Semisupervised Adversarial Neural Networks for Cyber Security Transfer Learning
标题:用于网络安全转移学习的半监督对抗性神经网络
作者: Casey Kneale, Kolia Sadeghi
链接:https://arxiv.org/abs/1907.11129
【6】 Graph Neural Lasso for Dynamic Network Regression
标题:动态网络回归的图神经套索
作者: Yixin Chen, Jiawei Zhang
链接:https://arxiv.org/abs/1907.11114
【7】 Filter Bank Regularization of Convolutional Neural Networks
标题:卷积神经网络的滤波器组正则化
作者: Seyed Mehdi Ayyoubzadeh, Xiaolin Wu
链接:https://arxiv.org/abs/1907.11110
【8】 The Good, the Bad and the Ugly: Augmenting a black-box model with expert knowledge
标题:好的,坏的和丑陋的:用专家知识扩充黑盒模型
作者: Raoul Heese, Michael Bortz
备注:International Conference on Artificial Neural Networks (ICANN) 2019
链接:https://arxiv.org/abs/1907.11105
【9】 Automated Discovery and Classification of Training Videos for Career Progression
标题:职业发展培训视频的自动发现和分类
作者: Alan Chern, Mohammed Korayem
链接:https://arxiv.org/abs/1907.11086
【10】 Towards Generalizing Sensorimotor Control Across Weather Conditions
标题:向推广跨越天气条件的传感器运动控制
作者: Qadeer Khan, Laura Leal-Taixé
备注:Accepted for publication in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
链接:https://arxiv.org/abs/1907.11025
【11】 Dynamic Input for Deep Reinforcement Learning in Autonomous Driving
标题:自主驾驶中深度强化学习的动态输入
作者: Maria Huegle, Joschka Boedecker
备注:Accepted at IROS 2019
链接:https://arxiv.org/abs/1907.10994
【12】 Overfitting of neural nets under class imbalance: Analysis and improvements for segmentation
标题:类不平衡下的神经网络过拟合:分割分析与改进
作者: Zeju Li, Ben Glocker
备注:Accepted at MICCAI 2019
链接:https://arxiv.org/abs/1907.10982
【13】 Learning higher-order logic programs
标题:学习高阶逻辑程序
作者: Andrew Cropper, Stephen H. Muggleton
链接:https://arxiv.org/abs/1907.10953
【14】 Logical reduction of metarules
标题:代谢物的逻辑归约
作者: Andrew Cropper, Sophie Tourret
链接:https://arxiv.org/abs/1907.10952
【15】 Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
标题:基于子空间并的随机几何图的谱方法理论
作者: Gen Li, Yuantao Gu
链接:https://arxiv.org/abs/1907.10906
【16】 The Truly Deep Graph Convolutional Networks for Node Classification
标题:用于节点分类的真正深图卷积网络
作者: Yu Rong, Junzhou Huang
链接:https://arxiv.org/abs/1907.10903
【17】 Optuna: A Next-generation Hyperparameter Optimization Framework
标题:Optuna:下一代超参数优化框架
作者: Takuya Akiba, Masanori Koyama
备注:10 pages, Accepted at KDD 2019 Applied Data Science track
链接:https://arxiv.org/abs/1907.10902
【18】 Simultaneous multi-view instance detection with learned geometric soft-constraints
标题:具有学习几何软约束的同时多视图实例检测
作者: Ahmed Samy Nassar, Jan D. Wegner
备注:Internationcal Conference on Computer Vision 2019 (ICCV 19)
链接:https://arxiv.org/abs/1907.10892
【19】 Framelet Pooling Aided Deep Learning Network : The Method to Process High Dimensional Medical Data
标题:Framelet Pooling辅助深度学习网络:处理高维医学数据的方法
作者: Chang Min Hyun, Jin Keun Seo
链接:https://arxiv.org/abs/1907.10834
【20】 Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning
标题:作为深度强化学习辅助任务的终端预测
作者: Bilal Kartal, Matthew E. Taylor
备注:AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'19). arXiv admin note: text overlap with arXiv:1812.00045
链接:https://arxiv.org/abs/1907.10827
【21】 Enhancing Adversarial Example Transferability with an Intermediate Level Attack
标题:通过中级攻击增强对抗实例的可转移性
作者: Qian Huang, Ser-Nam Lim
备注:ICCV 2019. arXiv admin note: text overlap with arXiv:1811.08458
链接:https://arxiv.org/abs/1907.10823
【22】 Machine learning approach to remove ion interference effect in agricultural nutrient solutions
标题:消除农业营养液中离子干扰效应的机器学习方法
作者: Byunghyun Ban, Minwoo Lee
链接:https://arxiv.org/abs/1907.10794
【23】 Towards AutoML in the presence of Drift: first results
标题:在漂移存在的情况下走向AutoML:第一个结果
作者: Jorge G. Madrid, Michele Sebag
备注:AutoML 2018 @ ICML/IJCAI-ECAI
链接:https://arxiv.org/abs/1907.10772
【24】 Sampled Softmax with Random Fourier Features
标题:具有随机傅立叶特征的采样Softmax
作者: Ankit Singh Rawat, Sanjiv Kumar
链接:https://arxiv.org/abs/1907.10747
【25】 Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
标题:基于Hessian的深网SGD分析:动力学与泛化
作者: Xinyan Li, Arindam Banerjee
链接:https://arxiv.org/abs/1907.10732
【26】 Automatic crack detection and classification by exploiting statistical event descriptors for Deep Learning
标题:利用统计事件描述子进行深度学习的自动裂纹检测和分类
作者: Giulio Siracusano, Giovanni Finocchio
链接:https://arxiv.org/abs/1907.10709
【27】 Benchmarking TPU, GPU, and CPU Platforms for Deep Learning
标题:针对深度学习对TPU、GPU和CPU平台进行基准测试
作者: Yu (Emma) Wang, David Brooks
链接:https://arxiv.org/abs/1907.10701
【28】 ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks
标题:ART:可证明正确的神经网络的抽象求精指导训练
作者: Xuankang Lin, Suresh Jagannathan
链接:https://arxiv.org/abs/1907.10662
【29】 Curriculum based Dropout Discriminator for Domain Adaptation
标题:用于领域适应的基于课程的Dropout鉴别器
作者: Vinod Kumar Kurmi, Vinay P Namboodiri
备注:BMVC 2019 Accepted, Project Page: this https URL
链接:https://arxiv.org/abs/1907.10628
【30】 Real-time Event Detection on Social Data Streams
标题:社交数据流上的实时事件检测
作者: Mateusz Fedoryszak, Changtao Zhong
备注:Accepted as a full paper at KDD 2019 on April 29, 2019
链接:https://arxiv.org/abs/1907.11229
【31】 Multi-resolution Autoregressive Graph-to-Graph Translation for Molecules
标题:分子的多分辨率自回归图到图的转换
作者: Wengong Jin, Tommi Jaakkola
链接:https://arxiv.org/abs/1907.11223
【32】 Domain Generalization via Multidomain Discriminant Analysis
标题:通过多领域判别分析进行领域综合
作者: Shoubo Hu, Laiwan Chan
备注:UAI 2019
链接:https://arxiv.org/abs/1907.11216
【33】 Deep Learning Models to Predict Pediatric Asthma Emergency Department Visits
标题:深度学习模型预测小儿哮喘急诊就诊
作者: Xiao Wang, Vikas Chowdhry
链接:https://arxiv.org/abs/1907.11195
【34】 HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop
标题:HEIDL:通过深度学习和人在环学习语言表达
作者: Yiwei Yang, Prithviraj Sen
链接:https://arxiv.org/abs/1907.11184
【35】 On the bias of H-scores for comparing biclusters, and how to correct it
标题:论H-分值对双聚类比较的偏倚及其纠正方法
作者: Jacopo Di Iorio, Marzia A. Cremona
链接:https://arxiv.org/abs/1907.11142
【36】 Improving the Accuracy of Principal Component Analysis by the Maximum Entropy Method
标题:用最大熵方法提高主成分分析的精度
作者: Guihong Wan, Haim Schweitzer
链接:https://arxiv.org/abs/1907.11094
【37】 Info Intervention
标题:信息干预
作者: Gong Heyang, Zhu Ke
链接:https://arxiv.org/abs/1907.11090
【38】 The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
标题:虚拟膜片钳:从钙成像输入线虫膜电位
作者: Andrew Warrington, Frank Wood
链接:https://arxiv.org/abs/1907.11075
【39】 DeepDrawing: A Deep Learning Approach to Graph Drawing
标题:DeepDrawing:一种图形绘制的深度学习方法
作者: Yong Wang, Huamin Qu
链接:https://arxiv.org/abs/1907.11040
【40】 Visualization of Emergency Department Clinical Data for Interpretable Patient Phenotyping
标题:可解释患者表型的急诊科临床数据可视化
作者: Nathan C. Hurley, Bobak J. Mortazavi
链接:https://arxiv.org/abs/1907.11039
【41】 Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
标题:不要担心天气:无监督的条件依赖域适应
作者: Horia Porav, Paul Newman
备注:Presented at ITSC2019
链接:https://arxiv.org/abs/1907.11004
【42】 Personalised novel and explainable matrix factorisation
标题:个性化的新颖和可解释的矩阵分解
作者: Ludovik Coba, Markus Zanker
链接:https://arxiv.org/abs/1907.11000
【43】 Y-Autoencoders: disentangling latent representations via sequential-encoding
标题:Y-自动编码器:通过顺序编码解除潜在表示的纠缠
作者: Massimiliano Patacchiola, Edward Rosten
链接:https://arxiv.org/abs/1907.10949
【44】 Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networks
标题:利用概率稠密位移网络缩小深度图像配准与常规图像配准之间的差距
作者: Mattias P. Heinrich
备注:accepted for publication at MICCAI 2019, open source code available at this https URL
链接:https://arxiv.org/abs/1907.10931
【45】 Self-supervised Domain Adaptation for Computer Vision Tasks
标题:计算机视觉任务的自监督域自适应
作者: Jiaolong Xu, Antonio M. Lopez
链接:https://arxiv.org/abs/1907.10915
【46】 Invariance reduces Variance: Understanding Data Augmentation in Deep Learning and Beyond
标题:不变减少方差:理解深度学习和超越中的数据增强
作者: Shuxiao Chen, Jane H Lee
链接:https://arxiv.org/abs/1907.10905
【47】 How to Manipulate CNNs to Make Them Lie: the GradCAM Case
标题:如何操纵CNN使其说谎:GradCAM案例
作者: Tom Viering, Elmar Eisemann
链接:https://arxiv.org/abs/1907.10901
【48】 Fast generalization error bound of deep learning without scale invariance of activation functions
标题:无激活函数尺度不变性的深度学习快速泛化误差界
作者: Yoshikazu Terada, Ryoma Hirose
链接:https://arxiv.org/abs/1907.10900
【49】 Adaptive Noise Injection: A Structure-Expanding Regularization for RNN
标题:自适应噪声注入:RNN的结构扩展正则化
作者: Rui Li, Sen Su
链接:https://arxiv.org/abs/1907.10885
【50】 Interpretability Beyond Classification Output: Semantic Bottleneck Networks
标题:分类输出之外的可解释性:语义瓶颈网络
作者: Max Losch, Bernt Schiele
链接:https://arxiv.org/abs/1907.10882
【51】 Forecasting Mobile Traffic with Spatiotemporal correlation using Deep Regression
标题:利用深度回归预测具有时空相关性的移动流量
作者: Giulio Siracusano, Aurelio La Corte
链接:https://arxiv.org/abs/1907.10865
【52】 Learning Resolution-Invariant Deep Representations for Person Re-Identification
标题:学习分解-用于个人重新识别的不变深度表示
作者: Yun-Chun Chen, Yu-Chiang Frank Wang
备注:Accepted to AAAI 2019 (Oral)
链接:https://arxiv.org/abs/1907.10843
【53】 Hard-Aware Fashion Attribute Classification
标题:硬感知时尚属性分类
作者: Yun Ye, Tao Mei
链接:https://arxiv.org/abs/1907.10839
【54】 Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization
标题:向ActivityNet挑战2019年提交:任务B时空操作本地化
作者: Chunfei Ma, Seungji Yang
链接:https://arxiv.org/abs/1907.10837
【55】 On Mining IoT Data for Evaluating the Operation of Public Educational Buildings
标题:公共教育建筑运营评价的物联网数据挖掘
作者: Na Zhu, Ioannis Chatzigiannakis
备注:13 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:1805.09561
链接:https://arxiv.org/abs/1907.10818
【56】 Co-Evolutionary Compression for Unpaired Image Translation
标题:用于不配对图像平移的协同进化压缩
作者: Han Shu, Chang Xu
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1907.10804
【57】 Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
标题:使用基于特征散射的对抗训练防御对抗攻击
作者: Haichao Zhang, Jianyu Wang
链接:https://arxiv.org/abs/1907.10764
【58】 One-stage Shape Instantiation from a Single 2D Image to 3D Point Cloud
标题:从单个2D图像到3D点云的一阶段形状实例化
作者: Xiao-Yun Zhou, Guang-Zhong Yang
备注:8.5 pages, 5 figures, MICCAI 2019
链接:https://arxiv.org/abs/1907.10763
【59】 Bilingual Lexicon Induction through Unsupervised Machine Translation
标题:基于无监督机器翻译的双语词汇归纳
作者: Mikel Artetxe, Eneko Agirre
备注:ACL 2019
链接:https://arxiv.org/abs/1907.10761
【60】 Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
标题:通过协同语义推理与深度学习模型的视觉交互
作者: Sebastian Gehrmann, Alexander M. Rush
备注:IEEE VIS 2019 (VAST)
链接:https://arxiv.org/abs/1907.10739
【61】 Careful Selection of Knowledge to solve Open Book Question Answering
标题:精心选择知识解决开卷问答
作者: Pratyay Banerjee, Chitta Baral
备注:Accepted to ACL 2019
链接:https://arxiv.org/abs/1907.10738
【62】 Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
标题:联合对抗训练:合并空间攻击和像素攻击
作者: Haichao Zhang, Jianyu Wang
链接:https://arxiv.org/abs/1907.10737
【63】 Cross-Attention End-to-End ASR for Two-Party Conversations
标题:两方对话的交叉关注端到端ASR
作者: Suyoun Kim, Florian Metze
备注:Interspeech 2019
链接:https://arxiv.org/abs/1907.10726
【64】 Deep Generative Quantile-Copula Models for Probabilistic Forecasting
标题:概率预测的深生成分位数-Copula模型
作者: Ruofeng Wen, Kari Torkkola
备注:Published at the 36th International Conference on Machine Learning (ICML2019), Time Series Workshop, Long Beach, California, 2019
链接:https://arxiv.org/abs/1907.10697
【65】 Semi-parametric Object Synthesis
标题:半参数对象综合
作者: Andrea Palazzi, Rita Cucchiara
链接:https://arxiv.org/abs/1907.10634
【66】 A neural network based post-filter for speech-driven head motion synthesis
标题:一种基于神经网络的语音驱动头部运动合成后置滤波器
作者: JinHong Lu, Hiroshi Shimodaira
链接:https://arxiv.org/abs/1907.10585
翻译:腾讯翻译君
网友评论