paper_reading_classes

Classes list

2017-10: First paper reading classes serise

• topic: deep learning
• objective: Understanding rescent history of deep learning
• paper list:
  • [0] (学生阅读)LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015): 436-444. pdf (Three Giants' Survey)
  • [1] （管）Hinton, Geoffrey E., Simon Osindero, and Yee-Whye Teh. "A fast learning algorithm for deep belief nets." Neural computation 18.7 (2006): 1527-1554. pdf (Deep Learning Eve)
  • [2] （邓）Hinton, Geoffrey E., and Ruslan R. Salakhutdinov. "Reducing the dimensionality of data with neural networks." Science 313.5786 (2006): 504-507. pdf (Milestone, Show the promise of deep learning)
  • [3] （李）Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012. pdf (AlexNet, Deep Learning Breakthrough)
  • [4] （赵）Vincent Dumoulin and Francesco Visin. "A guide for convolution arithmetic for deep learning" pdf
  • [5] （彭）DenseNet. Densely Connected Convolutional Networks.
  • [6] （管）Graves, Alex, Abdel-rahman Mohamed, and Geoffrey Hinton. "Speech recognition with deep recurrent neural networks." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013. pdf (RNN)
  • [7] （李）Jaderberg, Max, et al. "Decoupled neural interfaces using synthetic gradients." arXiv preprint arXiv:1608.05343 (2016). pdf (Innovation of Training Method,Amazing Work)
  • [8] （赵）Kenji Kawaguchi. "Deep Learning without Poor Local Minima" pdf (great work on fundation of deep learning)

Convolutional Neural Networks Architectures [by PP]

• [1] AlexNet. ImageNet Classification with Deep Convolutional Neural Networks.
• [2] VGG-Net. Very Deep Convolutional Networks for Large-Scale Image Recognition.
• [3] GooLeNet. Going Deeper with Convolutions.
• [4] InceptionV3. Rethinking the Inception Architecture for Computer Vision.
• [5] ResNet. Deep Residual Learning for Image Recognition.
• [6] InceptionV4. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning.
• [7] Deep Networks with Stochastic Depth.
• [8] （彭）DenseNet. Densely Connected Convolutional Networks.
• [9] Multi-Scale DenseNet. Multi-Scale Dense Convolutional Networks for Efficient Prediction.
• [10] Xception. Xception: Deep Learning with Depthwise Separable Convolutions.

 

Theory of Deep learning papers:

• [0] Hinton, Boltzmann machine related papers.Introduction
• [1] information geometry and Boltzmann machine related papers. Geometry and Expressive Power of Conditional Restricted Boltzmann Machines
• [2] Naftali Tishby, Information Theory of Deep Learning.
• [3] 中文材料波尔兹曼机
• [4] 会议Deep Learning: Theory, Algorithms, and Applications. Berlin, June 2017