人工智能每日论文速递[12.06]

同步公众号(arXiv每日论文速递),欢迎关注,感谢支持哦~


cs.AI 方向,今日共计30篇

【1】 Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation
标题:克隆群:通过模仿学习预测和控制多机器人系统
作者: Siyu Zhou, Heni Ben Amor
链接:arxiv.org/abs/1912.0281

【2】 Duty to Warn in Strategic Games
标题:战略游戏中的警示职责
作者: Pavel Naumov, Jia Tao
链接:arxiv.org/abs/1912.0275

【3】 Solving Advanced Argumentation Problems with Answer Set Programming
标题:用答案集编程解决高级论证问题
作者: Gerhard Brewka, Stefan Woltran
链接:arxiv.org/abs/1912.0273

【4】 An Interpretable Prediction Model for Obesity Prediction using EHR Data
标题:利用EHR数据预测肥胖的可解释预测模型
作者: Mehak Gupta, Rahmatollah Beheshti
链接:arxiv.org/abs/1912.0265

【5】 Reinforcement Learning with Non-Markovian Rewards
标题:非马尔可夫奖励的强化学习
作者: Maor Gaon, Ronen I. Brafman
备注:To Appear in AAAI 2020
链接:arxiv.org/abs/1912.0255

【6】 Towards Explainable Deep Neural Networks (xDNN)
标题:面向可解释深度神经网络(XDNN)
作者: Plamen Angelov, Eduardo Soares
链接:arxiv.org/abs/1912.0252

【7】 Inter-Level Cooperation in Hierarchical Reinforcement Learning
标题:分层强化学习中的层间合作
作者: Abdul Rahman Kreidieh, Alexandre M. Bayen
链接:arxiv.org/abs/1912.0236

【8】 Improving Policies via Search in Cooperative Partially Observable Games
标题:合作部分可观测博弈中的搜索改进策略
作者: Adam Lerer, Noam Brown
链接:arxiv.org/abs/1912.0231

【9】 Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning
标题:用于深度多智能体强化学习的简化动作解码器
作者: Hengyuan Hu, Jakob N Foerster
链接:arxiv.org/abs/1912.0228

【10】 Inferring the Optimal Policy using Markov Chain Monte Carlo
标题:用马尔可夫链蒙特卡罗推断最优策略
作者: Brandon Trabucco, Ganeshkumar Ashokavardhanan
链接:arxiv.org/abs/1912.0271

【11】 Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs
标题:鲁棒MDP的范数有界加权模糊集优化
作者: Reazul Hasan Russel, Marek Petrik
备注:arXiv admin note: substantial text overlap with arXiv:1910.10786
链接:arxiv.org/abs/1912.0269

【12】 Effect of Imbalanced Datasets on Security of Industrial IoT Using Machine Learning
标题:基于机器学习的不平衡数据集对工业物联网安全性的影响
作者: Maede Zolanvari, Raj Jain
备注:arXiv admin note: substantial text overlap with arXiv:1911.05771
链接:arxiv.org/abs/1912.0265

【13】 A Comprehensive Survey on Machine Learning Techniques and User Authentication Approaches for Credit Card
Fraud Detection
标题:信用卡欺诈检测中的机器学习技术和用户认证方法综述
作者: Niloofar Yousefi, Ivan Garibay
链接:arxiv.org/abs/1912.0262

【14】 Learning to synthesise the ageing brain without longitudinal data
标题:学习在没有纵向数据的情况下合成老化的大脑
作者: Tian Xia, Sotirios A. Tsaftaris
链接:arxiv.org/abs/1912.0262

【15】 Is perturbation an effective restart strategy?
标题:扰动是有效的重新启动策略吗?
作者: Aldeida Aleti, Markus Wagner
链接:arxiv.org/abs/1912.0253

【16】 Iterative Policy-Space Expansion in Reinforcement Learning
标题:强化学习中的迭代策略空间扩展
作者: Jan Malte Lichtenberg, Özgür Şimşek
备注:Workshop on Biological and Artificial Reinforcement Learning at the 33rd Conference on Neural Information
Processing Systems (NeurIPS 2019), Vancouver, Canada
链接:arxiv.org/abs/1912.0253

【17】 MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning
标题:MetalGAN:使用cGAN和元学习的多域无标签图像合成
作者: Tomaso Fontanini, Andrea Prati
链接:arxiv.org/abs/1912.0249

【18】 Towards Robust Neural Vocoding for Speech Generation: A Survey
标题:用于语音生成的鲁棒神经声编码:综述
作者: Po-chun Hsu, Hung-yi Lee
备注:Submitted to ICASSP 2020
链接:arxiv.org/abs/1912.0246

【19】 Analysis of the Optimization Landscapes for Overcomplete Representation Learning
标题:过完备表征学习的优化环境分析
作者: Qing Qu, Zhihui Zhu
链接:arxiv.org/abs/1912.0242

【20】 Zero-Shot Generation of Human-Object Interaction Videos
标题:人物交互视频的零射击生成
作者: Megha Nawhal, Leonid Sigal
链接:arxiv.org/abs/1912.0240

【21】 Towards Robust Relational Causal Discovery
标题:走向稳健的关系因果发现
作者: Sanghack Lee, Vasant Honavar
链接:arxiv.org/abs/1912.0239

【22】 SemEval-2015 Task 10: Sentiment Analysis in Twitter
标题:SemEval-2015任务10:Twitter中的情感分析
作者: Sara Rosenthal, Veselin Stoyanov
链接:arxiv.org/abs/1912.0238

【23】 Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline
标题:大规模视觉对话前培训:一种简单的最新基线
作者: Vishvak Murahari, Abhishek Das
链接:arxiv.org/abs/1912.0237

【24】 Information Retrieval and Its Sister Disciplines
标题:信息检索及其姊妹学科
作者: Grace Hui Yang
链接:arxiv.org/abs/1912.0234

【25】 Scratch that! An Evolution-based Adversarial Attack against Neural Networks
标题:抓紧那个!一种基于进化的神经网络对抗攻击
作者: Malhar Jere, Farinaz Koushanfar
链接:arxiv.org/abs/1912.0231

【26】 12-in-1: Multi-Task Vision and Language Representation Learning
标题:12合1:多任务愿景和语言表征学习
作者: Jiasen Lu, Stefan Lee
链接:arxiv.org/abs/1912.0231

【27】 Angular Visual Hardness
标题:角度视觉硬度
作者: Beidi Chen, Anima Anandkumar
链接:arxiv.org/abs/1912.0227

【28】 A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks
标题:网络安全任务中对抗性机器学习的博弈论方法综述
作者: Prithviraj Dasgupta, Joseph B. Collins
链接:arxiv.org/abs/1912.0225

【29】 Let's Get Dirty: GAN Based Data Augmentation for Soiling and Adverse Weather Classification in Autonomous
Driving
标题:让我们得到Dirty:基于GAN的数据增强,用于自主驾驶中的污垢和不利天气分类
作者: Michal Uricar, Senthil Yogamani
链接:arxiv.org/abs/1912.0224

【30】 Learning from Interventions using Hierarchical Policies for Safe Learning
标题:从使用安全学习分层策略的干预中学习
作者: Jing Bi, Chenliang Xu
备注:Accepted for publication at the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20)
链接:arxiv.org/abs/1912.0224

机器翻译,仅供参考

编辑于 2019-12-06 13:30