Unsupervised Deep Learning – ICLR 2017 Discoveries

简介:
  1. Unsupervised Learning Using Generative Adversarial Training And Clustering – Authors: Vittal Premachandran, Alan L. Yuille

  2. An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax– Authors: Wentao Huang, Kechen Zhang

  3. Unsupervised Cross-Domain Image Generation – Authors: Yaniv Taigman, Adam Polyak, Lior Wolf

  4. Unsupervised Perceptual Rewards for Imitation Learning – Authors: Pierre Sermanet, Kelvin Xu, Sergey Levine

  5. Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning – Authors: William Lotter, Gabriel Kreiman, David Cox

  6. Unsupervised sentence representation learning with adversarial auto-encoder – Authors: Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang

  7. Unsupervised Program Induction with Hierarchical Generative Convolutional Neural Networks – Authors: Qucheng Gong, Yuandong Tian, C. Lawrence Zitnick

  8. Generalizable Features From Unsupervised Learning – Authors: Mehdi Mirza, Aaron Courville, Yoshua Bengio

  9. Reinforcement Learning with Unsupervised Auxiliary Tasks – Authors: Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu

  10. Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data – Authors: Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt

  11. Unsupervised Learning of State Representations for Multiple Tasks – Authors: Antonin Raffin, Sebastian Hfer, Rico Jonschkowski, Oliver Brock, Freek Stulp

  12. Unsupervised Pretraining for Sequence to Sequence Learning – Authors: Prajit Ramachandran, Peter J. Liu, Quoc V. Le

  13. Unsupervised Deep Learning of State Representation Using Robotic Priors – Authors: Timothee LESORT, David FILLIAT

  14. Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders – Authors: Nat Dilokthanakul, Pedro A. M. Mediano, Marta Garnelo, Matthew C.H. Lee, Hugh Salimbeni, Kai Arulkumaran, Murray Shanahan

  15. Deep unsupervised learning through spatial contrasting – Authors: Elad Hoffer, Itay Hubara, Nir Ailon

https://www.youtube.com/watch?v=rK6bchqeaN8

https://amundtveit.com/

wKioL1gpI2aDSbfmAAGnnWLOSv8936.jpg

http://mp.weixin.qq.com/s?__biz=MzI3MTA0MTk1MA==&mid=2651989467&idx=1&sn=01610b4809f7c5c31bad2589926006cd&chksm=f121512ac656d83cfa5b7566e301738d46b8097b58aea724b1a94b183077f9538871346142d3&mpshare=1&scene=23&srcid=1113gx5LrBwRORmJHjd7lZOe#rd

http://it.sohu.com/20161113/n473045543.shtml

https://baijiahao.baidu.com/s?id=1550404872422873&wfr=spider&for=pc






     本文转自stock0991 51CTO博客,原文链接:http://blog.51cto.com/qing0991/1872533,如需转载请自行联系原作者




相关文章
|
机器学习/深度学习 搜索推荐 算法
Learning Disentangled Representations for Recommendation | NIPS 2019 论文解读
近年来随着深度学习的发展,推荐系统大量使用用户行为数据来构建用户/商品表征,并以此来构建召回、排序、重排等推荐系统中的标准模块。普通算法得到的用户商品表征本身,并不具备可解释性,而往往只能提供用户-商品之间的attention分作为商品粒度的用户兴趣。我们在这篇文章中,想仅通过用户行为,学习到本身就具备一定可解释性的解离化的用户商品表征,并试图利用这样的商品表征完成单语义可控的推荐任务。
23828 0
Learning Disentangled Representations for Recommendation | NIPS 2019 论文解读
|
机器学习/深度学习 算法 API
论文笔记之:Deep Reinforcement Learning with Double Q-learning
Deep Reinforcement Learning with Double Q-learning Google DeepMind   Abstract    主流的 Q-learning 算法过高的估计在特定条件下的动作值。
|
5月前
|
机器学习/深度学习 数据采集 人工智能
Supervised Learning
【6月更文挑战第7天】
45 2
|
6月前
|
算法 C语言 数据安全/隐私保护
C learning_6
C learning_6
|
6月前
|
存储 缓存 安全
C learning_4
C learning_4
|
6月前
|
存储 API 数据安全/隐私保护
C learning_7
C learning_7
|
机器学习/深度学习 语音技术
“Zero-shot Learning”、“One-shot Learning”和“Few-shot Learning”
你知道吗?在机器学习的世界里,有一种名为“Zero-shot Learning”、“One-shot Learning”和“Few-shot Learning”的策略,它们主要是为了解决神经网络模型因为训练数据少,导致模型泛化能力差的问题。
239 1
|
机器学习/深度学习 人工智能 自动驾驶
Reinforcement Learning
强化学习(Reinforcement Learning,简称 RL)是机器学习中的一种方法,主要用于训练智能体(Agent)在不确定环境中做出最佳决策。强化学习通过反复试验,根据智能体采取的行动所产生的奖励或惩罚信号来调整其行为策略。与监督学习和无监督学习不同,强化学习是一种无模型学习方法,不需要大量标注数据。
71 3
|
机器学习/深度学习 Web App开发 算法
强化学习(Reinforcement Learning)
强化学习(Reinforcement Learning)是机器学习的一个分支,旨在让智能体(agent)通过与环境的交互学习如何做出决策以最大化累积奖励。在强化学习中,智能体通过试错的方式与环境进行交互,并根据环境的反馈(奖励或惩罚)调整自己的行为。
177 2
|
机器学习/深度学习 算法 数据挖掘
【RLchina第六讲】Imitation Learning
【RLchina第六讲】Imitation Learning