人工智能论文速递【22篇论文资料】

【1】 Learning to Answer Ambiguous Questions with Knowledge Graph

标题:用知识图学习回答模棱两可的问题

作者: Yikai Zhu, Ming Zhang 

链接:https://arxiv.org/abs/1912.11668

【2】 A Logical Model for Supporting Social Commonsense Knowledge Acquisition

标题:支持社会常识知识获取的逻辑模型

作者: Zhenzhen Gu, Yuefei Sui 

链接:https://arxiv.org/abs/1912.11599

【3】 Learning by Cheating

标题:作弊学习

作者: Dian Chen, Philipp Krähenbühl 

备注:Paper published in CoRL2019

链接:https://arxiv.org/abs/1912.12294

【4】 Bitopological Duality for Algebras of Fittings logic and Natural Duality extension

标题:装配逻辑代数的双拓扑对偶与自然对偶扩张

作者: Litan Kumar Das, Kumar Sankar Ray 

链接:https://arxiv.org/abs/1912.12223

【5】 Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data

标题:联邦模拟学习:一种面向异构传感器数据的云机器人系统框架

作者: Boyi Liu, Cheng-Zhong Xu 

备注:arXiv admin note: substantial text overlap with arXiv:1909.00895

链接:https://arxiv.org/abs/1912.12204

【6】 Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency

标题:解释您的行动:使用聚焦功能显着性了解座席操作

作者: Piyush Gupta, Balaji Krishnamurthy 

备注:Accepted at the International Conference on Learning Representations (ICLR) 2020

链接:https://arxiv.org/abs/1912.12191

【7】 Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking

标题:用于工业拾取的大规模6D目标位姿估计数据集

作者: Kilian Kleeberger, Marco F. Huber 

备注:Accepted at 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)

链接:https://arxiv.org/abs/1912.12125

【8】 Evolutionary Clustering via Message Passing

标题:通过消息传递的进化聚类

作者: Natalia M. Arzeno, Haris Vikalo 

链接:https://arxiv.org/abs/1912.11970

【9】 On the Morality of Artificial Intelligence

标题:论人工智能的道德性

作者: Alexandra Luccioni, Yoshua Bengio 

链接:https://arxiv.org/abs/1912.11945

【10】 Smell Pittsburgh: Engaging Community Citizen Science for Air Quality

标题:嗅觉匹兹堡:参与社区公民科学促进空气质量

作者: Yen-Chia Hsu, Illah Nourbakhsh 

链接:https://arxiv.org/abs/1912.11936

【11】 Category-Level Articulated Object Pose Estimation

标题:类别级关节对象姿态估计

作者: Xiaolong Li, Shuran Song 

链接:https://arxiv.org/abs/1912.11913

【12】 Quasi-Newton Trust Region Policy Optimization

标题:拟牛顿信赖域策略优化

作者: Devesh Jha, Diego Romeres 

备注:3rd Conference on Robot Learning (CoRL 2019)

链接:https://arxiv.org/abs/1912.11912

【13】 Convergence and sample complexity of gradient methods for the model-free linear quadratic regulator problem

标题:无模型线性二次型调节器问题梯度法的收敛性和样本复杂性

作者: Hesameddin Mohammadi, Mihailo R. Jovanović 

链接:https://arxiv.org/abs/1912.11899

【14】 A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning

标题:基于知识的推理与机器学习相结合的智能对象感知方法综述

作者: Filippos Gouidis, Dimitris Plexousakis 

链接:https://arxiv.org/abs/1912.11861

【15】 Feature-Attention Graph Convolutional Networks for Noise Resilient Learning

标题:用于噪声恢复学习的特征-注意图卷积网络

作者: Min Shi, Jianxun Liu 

链接:https://arxiv.org/abs/1912.11755

【16】 Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation

标题:基于Coursera语料库挖掘和多级微调的讲座翻译研究

作者: Haiyue Song, Sadao Kurohashi 

备注:10 pages, 1 figure, 9 tables, under review by LREC2020

链接:https://arxiv.org/abs/1912.11739

【17】 The Windfall Clause: Distributing the Benefits of AI for the Common Good

标题:意外之财条款:为共同利益分配AI的利益

作者: Cullen O'Keefe, Allan Dafoe 

链接:https://arxiv.org/abs/1912.11595

【18】 A Study of the Learnability of Relational Properties (Model Counting Meets Machine Learning)

标题:关系属性的可学习性研究(模型计数与机器学习)

作者: Muhammad Usman, Sarfraz Khurshid 

链接:https://arxiv.org/abs/1912.11580

【19】 Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro

标题:NumPyro中灵活和加速概率编程的组合效果

作者: Du Phan, Martin Jankowiak 

备注:10 pages, 2 figures; NeurIPS 2019 Program Transformations for Machine Learning Workshop

链接:https://arxiv.org/abs/1912.11554

【20】 Estudo comparativo de meta-heurísticas para problemas de colorações de grafos

标题:EStudo Comparativo de meta-Heurísticas para problemas de Coloraçées de grafos

作者: Flávio José Mendes Coelho 

链接:https://arxiv.org/abs/1912.11533

【21】 Pseudo Random Number Generation: a Reinforcement Learning approach

标题:伪随机数生成:一种强化学习方法

作者: Luca Pasqualini, Maurizio Parton 

链接:https://arxiv.org/abs/1912.11531

【22】 A Machine-Learning Approach for Earthquake Magnitude Estimation

标题:地震震级估计的机器学习方法

作者: S.Mostafa Mousavi, Gregory C. Beroza 

链接:https://arxiv.org/abs/1911.05975