Kaffaljidhmah2 / DL_PaperList

Paper List : Deep Learning Modern Techniques

Paper List : Deep Learning Modern Techniques

Remains to be updated. Not for wide circulation.

---

Part I : Network Layer

Fractional MaxPooling

Self-Normalizing Neural Networks

Improving neural networks by preventing co-adaptation of feature detectors

Efficient Object Localization Using Convolutional Networks

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

Language Modeling with Gated Convolutional Networks

---

Part II : Optimization

ADADELTA: An Adaptive Learning Rate Method

Adam: A Method for Stochastic Optimization

Generating Sequences With Recurrent Neural Networks

SGDR: Stochastic Gradient Descent with Warm Restarts

---

Reference : http://pytorch.org/docs