人工智能每日论文速递[08.20]

同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文。(* ̄rǒ ̄)

cs.AI 方向,今日共计28篇

[cs.AI]:

【1】 Computational Flight Control: A Domain-Knowledge-Aided Deep Reinforcement Learning Approach
标题:计算飞行控制:一种领域知识辅助的深度强化学习方法
作者: Hyo-Sang Shin, Antonios Tsourdos
链接:https://arxiv.org/abs/1908.06884

【2】 Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
标题:用于一次性模仿学习的符号规划器的连续松弛
作者: De-An Huang, Juan Carlos Niebles
备注:IROS 2019
链接:https://arxiv.org/abs/1908.06769

【3】 Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data
标题:利用深度神经网络和人类数据学习玩国际象棋变种Crazyhouse高于世界冠军水平
作者: Johannes Czech, Johannes Fürnkranz
备注:35 pages, 19 figures, 14 tables
链接:https://arxiv.org/abs/1908.06660

【4】 Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing
标题:从道路试验看自动驾驶汽车的安全性和可靠性
作者: Xingyu Zhao, Lorenzo Strigini
链接:https://arxiv.org/abs/1908.06540

【5】 Search Algorithms for Mastermind
标题:Mastermind的搜索算法
作者: Anthony D. Rhodes
链接:https://arxiv.org/abs/1908.06183

【6】 Message Passing for Complex Question Answering over Knowledge Graphs
标题:知识图上复杂问题回答的消息传递
作者: Svitlana Vakulenko, Michael Cochez
备注:Accepted in CIKM 2019
链接:https://arxiv.org/abs/1908.06917

【7】 An Autonomous Performance Testing Framework using Self-Adaptive Fuzzy Reinforcement Learning
标题:一种基于自适应模糊强化学习的自主性能测试框架
作者: Mahshid Helali Moghadam, Björn Lisper
链接:https://arxiv.org/abs/1908.06900

【8】 Efficient Discovery of Expressive Multi-label Rules using Relaxed Pruning
标题:使用松弛剪枝高效发现表现性多标签规则
作者: Yannik Klein, Eneldo Loza Mencía
备注:Preprint version. To appear in Proceedings of the 22nd International Conference on Discovery Science, 2019
链接:https://arxiv.org/abs/1908.06874

【9】 Towards Linearization Machine Learning Algorithms
标题:走向线性化的机器学习算法
作者: Steve Tueno
链接:https://arxiv.org/abs/1908.06871

【10】 Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition
标题:Wi-Fringe:在基于WiFi CSI的设备中利用文本语义-Free命名手势识别
作者: Md Tamzeed Islam, Shahriar Nirjon
链接:https://arxiv.org/abs/1908.06803

【11】 Iterative Update and Unified Representation for Multi-Agent Reinforcement Learning
标题:多Agent强化学习的迭代更新和统一表示
作者: Jiancheng Long, Bo Xu
链接:https://arxiv.org/abs/1908.06758

【12】 BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
标题:BOAH:一个用于多保真度贝叶斯优化和超参数分析的工具套件
作者: Marius Lindauer, Frank Hutter
链接:https://arxiv.org/abs/1908.06756

【13】 Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters
标题:贝叶斯优化自身超参数的影响评估
作者: Marius Lindauer, Frank Hutter
备注:Accepted at DSO workshop (as part of IJCAI'19)
链接:https://arxiv.org/abs/1908.06674

【14】 Intrinsically Motivated Exploration for Automated Discovery of Patterns in Morphogenetic Systems
标题:形态发生系统中模式自动发现的内在动机探索
作者: Chris Reinke, Pierre-Yves Oudeyer
链接:https://arxiv.org/abs/1908.06663

【15】 Transfer in Deep Reinforcement Learning using Knowledge Graphs
标题:基于知识图的深度强化学习中的迁移
作者: Prithviraj Ammanabrolu, Mark O. Riedl
链接:https://arxiv.org/abs/1908.06556

【16】 RefNet: A Reference-aware Network for Background Based Conversation
标题:RefNet:一个基于背景对话的参考感知网络
作者: Chuan Meng, Maarten de Rijke
链接:https://arxiv.org/abs/1908.06449

【17】 Understanding Cyber Athletes Behaviour Through a Smart Chair: CS:GO and Monolith Team Scenario
标题:通过智能椅子了解网络运动员的行为:CS:Go和Monolith团队场景
作者: Anton Smerdov, Evgeny Burnaev
链接:https://arxiv.org/abs/1908.06407

【18】 eSports Pro-Players Behavior During the Game Events: Statistical Analysis of Data Obtained Using the Smart Chair
标题:eSports Pro-Player在游戏事件中的行为:使用智能座椅获得的数据的统计分析
作者: Anton Smerdov, Andrey Somov
链接:https://arxiv.org/abs/1908.06402

【19】 VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation
标题:VUSFA:用于改进目标驱动视觉导航的传输DRL的变分通用后继特征近似器
作者: Shamane Siriwardhana, Suranga Nanayakkara
链接:https://arxiv.org/abs/1908.06376

【20】 Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation
标题:持续对抗性扰动下神经网络控制策略的验证
作者: Yuh-Shyang Wang, Luca Daniel
链接:https://arxiv.org/abs/1908.06353

【21】 EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation
标题:EigenRank by Committee:基于稳健深度学习的医学图像分割的数据子集选择和故障预测范例
作者: Bilwaj Gaonkar, Luke Macyszyn
链接:https://arxiv.org/abs/1908.06337

【22】 What is needed for simple spatial language capabilities in VQA?
标题:VQA中的简单空间语言功能需要什么?
作者: Alexander Kuhnle, Ann Copestake
链接:https://arxiv.org/abs/1908.06336

【23】 Prune Sampling: a MCMC inference technique for discrete and deterministic Bayesian networks
标题:剪枝抽样:一种用于离散和确定性贝叶斯网络的MCMC推理技术
作者: Frank Phillipson, Ron Weikamp
链接:https://arxiv.org/abs/1908.06335

【24】 Multi-View Broad Learning System for Primate Oculomotor Decision Decoding
标题:灵长类眼动决策解码的多视角宽学习系统
作者: Zhenhua Shi, Dongrui Wu
链接:https://arxiv.org/abs/1908.06180

【25】 Distributional Negative Sampling for Knowledge Base Completion
标题:用于知识库完成的分布式负抽样
作者: Sarthak Dash, Alfio Gliozzo
链接:https://arxiv.org/abs/1908.06178

【26】 Oxford Handbook on AI Ethics Book Chapter on Race and Gender
标题:牛津人工智能伦理手册种族与性别章节
作者: Timnit Gebru
链接:https://arxiv.org/abs/1908.06165

【27】 Learning Representations and Agents for Information Retrieval
标题:信息检索的学习表示和Agent
作者: Rodrigo Nogueira
链接:https://arxiv.org/abs/1908.06132

【28】 Symmetric Cross Entropy for Robust Learning with Noisy Labels
标题:带噪声标签的对称交叉熵鲁棒学习
作者: Yisen Wang, James Bailey
备注:ICCV2019
链接:https://arxiv.org/abs/1908.06112

翻译:腾讯翻译君

你可能感兴趣的:(人工智能每日论文速递[08.20])