Skip to content
Summaries, notes, questions on Deep Learning research papers.
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea The Case for Learned Index Structures Mar 15, 2018
papers The Case for Learned Index Structures Mar 15, 2018
talks Fixing broken links. Dec 10, 2017

Paper notes

Related: my flashcards repo.


  • The Case for Learned Index Structures [notes] [link]


  • Bayesian Methods for Hackers, Chapter 2 [notes] [link]
  • Bayesian Methods for Hackers, Chapter 1 [notes] [link]
  • Stability and Generalization [notes] [link]


  • Overheard at NIPS '17 [notes]
  • Learning disentangled representations for RL [notes]
  • Inductive Representation Learning on Large Graphs [notes]
  • Style Transfer from Non-parallel Text by Cross-Alignment [notes]
  • Counterfactual fairness [notes]
  • Probabilistic methods spotlights [notes]
  • Algorithms spotlights [notes]
  • Interpretibility spotlights [notes]
  • Architectures spotlights [notes]
  • Learning State Representations [notes]
  • Overcoming Limited Data with GANs [notes]
  • What’s so Hard About Natural Language Understanding? [notes]
  • Probabilistic Programming with Pyro [notes]
  • Exploring the different paths to achievingtalks/ disentangled representations [notes]
  • Priors to help automatically discover and disentangle explanatory factors [notes]
  • Interpretable Discovery in Large Image Data Sets [notes]
  • Generative Adversarial Imitation Learning [notes]
  • Translating a Trillion Points of Data into Diagnostics, Therapies and New Insights in Health & Disease [notes]
  • Causal inference, ML for the developing world [notes]
  • Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning [notes]
  • Medical Machine Intelligence [notes]
  • ML for Health Keynote (Fei-Fei Li): Illuminating the Dark Spaces of Healthcare [notes]
  • Are GANs creative? [notes]
  • Computational Methods for Solving Developing World Problems [notes]
  • On Bayesian Deep Learning and Deep Bayesian Learning [notes]


  • Fairness in ML [notes]
  • A Primer on Optimal Transport [link] [notes]
  • Quick summaries: other generalization papers [notes]
  • Rethinking generalization requires revisiting old ideas [link] [notes]
  • Generalization in Deep Learning [link] [notes]
  • Understanding deep learning requires rethinking generalization [link] [notes]
  • Generative Adversarial Nets: An Overview [link] [notes]
  • Concrete Problems in AI Safety [link] [notes]
  • Dynamic Routing Between Capsules [link] [notes]


  • Quick summaries: Wasserstein GAN, BEGAN, Batch and Weight Normalization in GANs [notes]
  • Opportunities And Obstacles For Deep Learning In Biology And Medicine [link] [notes]
  • Single-Channel Multi-Speaker Separation using Deep Clustering [link] [notes]
  • Deep clustering: Discriminative embeddings for segmentation and separation [link] [notes]
  • Learning Hierarchical Features for Scene Labeling [link] [notes]
  • Pixel Recurrent Neural Networks [link] [notes]
  • Artistic Style Transfer For Videos [link] [notes]
  • Grammar as a Foreign Language [link] [notes]
  • Deep Convolutional Neural Network Design Patterns [link] [notes]
  • Massive Exploration of Neural Machine Translation Architectures [link] [notes]
  • Attention Is All You Need [link] [notes]


  • Quick summaries: attention papers [notes]
  • DeViSE: A Deep Visual-Semantic Embedding Model [link] [notes]
  • DRAW: Deep Recurrent Attentive Writer [link] [blog] md


  • A Biomedical Information Extraction Primer for NLP Researchers [link] [notes]
  • FaceNet: A Unified Embedding for Face Recognition and Clustering [link]
  • Neural Machine Translation by Jointly Learning to Align and Translate [link] [blog]
  • Enriching Word Vectors with Subword Information [link]
  • Bag of Tricks for Efficient Text Classification [link] [blog]
  • Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling [link] [blog]
  • GloVe: Global Vectors for Word Representations [link]
  • Recurrent Convolutional Neural Networks for Text Classification [link] [blog]


  • Hierarchical Multiscale Recurrent Neural Networks [link] [blog]
  • Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation [link]
  • Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding [link] [blog]


  • Resnet in Resnet: Generalizing Residual Architectures [link]
  • Residual Networks of Residual Networks: Multilevel Residual Networks [link] [notes]
  • Deep Residual Learning for Image Recognition [link] [notes]

Other collections of paper notes

  • Adrian Colyer [link]
  • Denny Britz [link]
  • Hoang Cuong [link]
  • Alexander Jung [link]
You can’t perform that action at this time.