kevinzakka / Research Paper Notes

Research Paper Library & Notes

This is a list papers that I’ve read with some summaries and implementation code. They are sorted in inverse chronological order with links to their respective arXiv page.

2018-04

• Gradient Estimation Using Stochastic Computation Graphs

2018-03

• Dimensionality Reduction by Learning an Invariant Mapping
• Siamese Neural Networks for One-shot Image Recognition

2018-02

• HYPERBAND: Bandit-Based Configuration Evaluation For Hyperparameter Optimization

2017-12

• The Case for Learned Index Structures

2017-09

• DRAW: A Recurrent Neural Network For Image Generation
• Recurrent Models of Visual Attention

2017-08

• Focal Loss for Dense Object Detection
• SGDR: Stochastic Gradient Descent With Warm Restarts
• FreezeOut: Accelerate Training By Progressively Freezing Layers
• Densely Connected Convolutional Networks

2017-06

• Learning to Reason: End-to-End Module Networks for Visual Question Answering
• Neural Module Networks
• Inferring and Executing Programs for Visual Reasoning
• Attention Is All You Need
  • summary
• Learning To Diagnose With LSTM Recurrent Neural Networks
• Self-Normalizing Neural Networks
  • summary
  • code

2017-05

• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial

2017-03

• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Image-to-Image Translation with Conditional Adversarial Networks
• Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

2017-01

• Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
• Automatic Chemical Design using a Data-Driven Continuous Representation of Molecules
• Generating Sequences from a Continuous Space

2016-12

• Language Modeling with Gated Convolutional Networks
• Spatial Transformer Networks
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution

2016-11

• Neural Machine Translation in Linear Time
  • summary

2016-10

• A Neural Algorithm of Artistic Style

2016-09

• On Large-Batch Training for Deep Learning
  • summary
• Batch Normalization
  • summary
  • code
• Dropout
  • summary