18. 人気トピック @ ICLR2017
● ニューラルネットの汎化性能について
○ Rethinking generalization https://arxiv.org/abs/1611.03530
○ Large batch training coverges to sharp minima https://arxiv.org/abs/1609.04836
● Generative Adversarial Networks
○ Towards principled methods of training GANs https://openreview.net/pdf?id=Hk4_qw5xe
○ Energy based GANs https://arxiv.org/abs/1702.01691
○ Two-sample tests by classifier https://openreview.net/forum?id=SJkXfE5xx¬eId=SJkXfE5xx
● Deep Reinforcement Learning
○ Reinforcement Learning with Unsupervised Auxiliary Tasks https://openreview.net/pdf?id=SJ6yPD5xg
○ (Not RL) Learning to act by predicting future https://arxiv.org/abs/1611.01779
● Neural Programmer
○ Making Neural Programming Architectures Generalize via Recursion
https://openreview.net/forum?id=BkbY4psgg¬eId=BkbY4psgg
19. Generative Adversarial Networks (GANs)
● オリジナルのアルゴリズムは Ian Goodfellow et al. (2014) によって提案
● 以降とても多くの論文がarXiv等で(乱発ぎみに)発表された。
○ GAN Zoo https://github.com/hindupuravinash/the-gan-zoo
https://github.com/hindupuravinash/the-gan-zoo
(GANs)