雷锋网AI科技评论:NIPS,中文名称为神经信息处理系统大会(Conference and Workshop on Neural Information Processing Systems),是一个关于机器学习和计算神经科学的国际会议,也是人工智能领域的A类会议。
AI科技评论消息,NIPS 2017 今年共录用论文678篇,目前全部论文名单还未对外公布,雷锋网通过各路消息汇总,为大家整理了部分录用论文。具体论文名单由官方发布为准。
微软亚洲研究院共录用四篇论文,刘铁岩老师第一时间在微博向大家汇报了这一好消息:
四篇论文分别是:
Deliberation Networks: Sequence Generation Beyond One-Pass Decoding
Decoding with Value Networks for Neural Machine Translation.
LightGBM: A Highly Efficient Gradient Boosting Decision Tree.
Finite sample analysis of the GTD Policy Evaluation Algorithms in Markov Setting.
Facebook AI实验室研究员田渊栋博士录用一篇 oral paper:
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
链接:https://arxiv.org/abs/1707.01067
宋佳铭,斯坦福博士一年级,现在在OpenAI实习,录用两篇NIPS论文:
Inferring The Latent Structure of Human Decision-Making from Raw Visual Inputs
链接:https://arxiv.org/abs/1703.08840
A-NICE-MC: Adversarial Training for MCMC
链接:https://arxiv.org/abs/1706.07561
美国哥伦比亚大学计算机学院助理教授,机器学习实验室主任Bert Huang 和他的学生 Sirui Yao 发表的论文:
Beyond Parity: Fairness Objectives for Collaborative Filtering
链接: https://arxiv.org/abs/1705.08804
卡内基梅隆大学博士生Noam Brown 录用一篇NIPS 2017 oral:
Safe and Nested Subgame Solving for Imperfect-Information Games
链接:https://arxiv.org/pdf/1705.02955.pdf
前谷歌大脑实习生,多伦多大学计算机学院机器学习博士生Alireza Makhzani 录用的论文题目是:
“PixelGAN Autoencoders” : semi-supervised learning with GAN inference networks and PixelCNN decoders
链接:https://arxiv.org/abs/1706.00531
贝叶斯方法研究团队(Bayesian Methods Research Group)录用论文为:
Structured Bayesian Pruning via Log-Normal Multiplicative Noise"
链接:https://arxiv.org/abs/1705.07283
前Facebook AI研究团队研究实习生,Torch7 卷积神经网络的主要发明者Jin-Hwa Kim,录用的的论文题目为:
Overcoming Catastrophic Forgetting by Incremental Moment Matching"
链接:https://arxiv.org/abs/1703.08475
阿姆斯特丹大学博士生Serhii Havrylov 录用的论文题目为:
Emergence of Language with Multi-agent Games
链接:https://arxiv.org/abs/1705.11192
谷歌大脑研究员、康奈尔大学博士生Maithra Raghu 录用的论文的题目是:
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Understanding and Improvement
链接:https://arxiv.org/abs/1706.05806
雷锋网AI科技评论报道