Home

Welcome to the 2019-winter-reading-project wiki!

Good paper list to start

1주차

• Very Deep Convolutional Networks for Large-scale Image Recognition
• Deep Residual Learning for Image Recognition
• Aggregated Residual Transformations for Deep Neural Networks
• Densely Connected Convolutional Networks
• Going deeper with convolutions

2주차

• Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Maxout Networks

3주차

• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Siamese Neural Networks for One-shot Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Discrete Variational Autoencoders
• GloVe: Global Vectors for Word Representation

4주차

• A guide to recurrent neural networks and backpropagation
• Gated Feedback Recurrent Neural Networks
• Attention Is All You Need
• Get To The Point: Summarization with Pointer-Generator Networks
• Neural Turing Machines

5주차

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Dynamic Network Surgery for Efficient DNNs
• Soft Weight-Sharing for Neural Network Compression
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

6주차

• Accelerating Neural Architecture Search using Performance Prediction
• A Tutorial on Bayesian Optimization
• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
• BOHB: Robust and Efficient Hyperparameter Optimization at Scale
• Population Based Training of Neural Networks

7주차

• Neural Architecture Search with Reinforcement Learning
• Evolving Deep Neural Networks
• Learning Transferable Architectures for Scalable Image Recognition
• Efficient Neural Architecture Search via Parameter Sharing
• DARTS: Differentiable Architecture Search