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.AI 方向,今日共计19篇
[cs.AI]:
【1】 Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning
标题:内存受限开环规划的自适应Thompson采样堆栈
作者: Thomy Phan, Claudia Linnhoff-Popien
备注:Accepted at IJCAI 2019. arXiv admin note: substantial text overlap with arXiv:1905.04020
链接:https://arxiv.org/abs/1907.05861
【2】 Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)
标题:利用因果关系进行动态贝叶斯网络中的选择性信念过滤(扩展摘要)
作者: Stefano V. Albrecht, Subramanian Ramamoorthy
备注:Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Journal Track, 2017. arXiv admin note: text overlap with arXiv:1401.7941
链接:https://arxiv.org/abs/1907.05850
【3】 A semi-holographic hyperdimensional representation system for hardware-friendly cognitive computing
标题:用于硬件友好认知计算的半全息高维表示系统
作者: A. Serb, T. Prodromakis
链接:https://arxiv.org/abs/1907.05688
【4】 Automatic Generation of Atomic Consistency Preserving Search Operators for Search-Based Model Engineering
标题:基于搜索的模型工程中保持原子一致性的搜索算子的自动生成
作者: Alexandru Burdusel, Stefan John
备注:Technical report version of the MODELS 2019 paper with the same title
链接:https://arxiv.org/abs/1907.05647
【5】 Learning an Urban Air Mobility Encounter Model from Expert Preferences
标题:从专家偏好中学习城市空中机动遭遇模型
作者: Sydney M. Katz, Mykel J. Kochenderfer
备注:8 pages, 7 figures, submitted to 2019 Digital Avionics Systems Conference
链接:https://arxiv.org/abs/1907.05575
【6】 MLR (Memory, Learning and Recognition): A General Cognitive Model -- applied to Intelligent Robots and Systems Control
标题:MLR(Memory,Learning and Recognition):一种通用认知模型-应用于智能机器人和系统控制
作者: Aras R. Dargazany
链接:https://arxiv.org/abs/1907.05553
【7】 Grounding Value Alignment with Ethical Principles
标题:以伦理原则为基础的价值取向
作者: Tae Wan Kim, John Hooker
链接:https://arxiv.org/abs/1907.05447
【8】 Augmenting Neural Nets with Symbolic Synthesis: Applications to Few-Shot Learning
标题:用符号综合增强神经网络:在少镜头学习中的应用
作者: Adithya Murali, P. Madhusudan
链接:https://arxiv.org/abs/1907.05878
【9】 DisCoRL: Continual Reinforcement Learning via Policy Distillation
标题:DisCoRL:通过策略蒸馏的持续强化学习
作者: René Traoré, David Filliat
备注:arXiv admin note: text overlap with arXiv:1906.04452
链接:https://arxiv.org/abs/1907.05855
【10】 Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
标题:基于检索的对话系统中响应选择的包含知识的ESIM模型
作者: Jatin Ganhotra, Kshitij Fadnis
备注:Ranked 2nd on Ubuntu and 4th on Advising task in DSTC-7 Track 1. Accepted for an oral presentation at the DSTC-7 workshop at AAAI 2019
链接:https://arxiv.org/abs/1907.05792
【11】 Why Blocking Targeted Adversarial Perturbations Impairs the Ability to Learn
标题:为什么阻断有针对性的对抗性扰动会损害学习能力
作者: Ziv Katzir, Yuval Elovici
链接:https://arxiv.org/abs/1907.05718
【12】 Rethink Global Reward Game and Credit Assignment in Multi-agent Reinforcement Learning
标题:对多智能体强化学习中全局奖励博弈和学分分配的再思考
作者: Jianhong Wang, Yunjie Gu
链接:https://arxiv.org/abs/1907.05707
【13】 From Observability to Significance in Distributed Information Systems
标题:从可观测性到分布式信息系统的重要性
作者: Mark Burgess
链接:https://arxiv.org/abs/1907.05636
【14】 Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling
标题:从负抽样的演示中学习可自我纠正的策略和价值函数
作者: Yuping Luo, Tengyu Ma
链接:https://arxiv.org/abs/1907.05634
【15】 Graph-Structured Visual Imitation
标题:图结构视觉模仿
作者: Maximilian Sieb, Katerina Fragkiadaki
链接:https://arxiv.org/abs/1907.05518
【16】 Artificial Intelligence as a Services (AI-aaS) on Software-Defined Infrastructure
标题:软件定义基础设施上的人工智能即服务(AI-AAS)
作者: Saeedeh Parsaeefard, Alberto Leon-Garcia
链接:https://arxiv.org/abs/1907.05505
【17】 Effective and General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping
标题:基于动态时间规整的指令条件导航有效性综合评价
作者: Gabriel Magalhaes, Jason Baldridge
链接:https://arxiv.org/abs/1907.05446
【18】 Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning
标题:模拟投影的程序强化学习策略梯度
作者: Abhinav Verma, Swarat Chaudhuri
链接:https://arxiv.org/abs/1907.05431
【19】 Ensuring Responsible Outcomes from Technology
标题:确保技术产生负责任的结果
作者: Aaditeshwar Seth
备注:Presented as an invited talk at IEEE COMSNETS 2019
链接:https://arxiv.org/abs/1907.03263
翻译:腾讯翻译君