Deep Learning Paper Review Intro

2019 겨울방학에 진행된 스터디에서 읽은 논문들을 정리해보았다.

• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
  • 2014, JMLR
  • http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf
  • Dropoput
• Learning Phrase Representations using RNN Encoder–Decoderfor Statistical Machine Translation
  • 2014, EMNLP
  • https://arxiv.org/abs/1406.1078
  • GRU
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
  • 2014, NIPS workshop
  • https://arxiv.org/abs/1412.3555
  • GRU vs LSTM
• Adam: A Method for Stochastic Optimization
  • 2015, ICLR
  • https://arxiv.org/abs/1412.6980
  • Adam optimizer
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
  • 2015, ICML
  • http://proceedings.mlr.press/v37/ioffe15.pdf
  • Batch normalization
• Explaining and Harnessing Adversarial Examples
  • 2015, ICLR
  • https://arxiv.org/abs/1412.6572
  • Adversarial
• How transferable are features in deep neural networks?
  • 2014, NIPS
  • https://papers.nips.cc/paper/5347-how-transferable-are-features-in-deep-neural-networks
  • Transfer learning
• Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 2015, ICLR
  • https://arxiv.org/abs/1409.1556
  • ImageNet
• Generative Adversarial Nets
  • 2014, NIPS
  • http://papers.nips.cc/paper/5423-generative-adversarial-nets
  • GANs