A list of useful resources and paper
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
README.md

README.md

Papers

Generalization

  • Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

Reparameterization

  • Implicit Reparameterization Gradients

Interpretable Models

  • Measuring the Intrinsic Dimension of Objective Landscapes
  • Insights on representational similarity in neural networks with canonical correlation

Variational Methods

  • Variational Inference and Deep Learning: A New Synthesis
  • Auto-Encoding Variational Bayes
  • An Introduction to Variational Methods for Graphical Models

Discrete Latent Space

  • Neural Discrete Representation Learning
  • The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
  • Categorical Reparameterization with Gumbel-Softmax

Policy Gradients

  • Trust Region Policy Optimization
  • Proximal Policy Optimization Algorithms
  • Deterministic Policy Gradient Algorithms
  • Continuous control with deep reinforcement learning

Actor Critic

  • Asynchronous Methods for Deep Reinforcement Learning
  • High-Dimensional Continuous Control Using Generalized Advantage Estimation

Q-Learning

  • Human-level control through deep reinforcement learning
  • Deep Reinforcement Learning with Double Q-learning

Energy Models

  • A Tutorial on Energy-Based Learning
  • An Introduction to Restricted Boltzmann Machines

Markov Models

  • A tutorial on hidden Markov models and selected applications in speech recognition

Program Synthesis

  • Supervised Sequence Labelling with Recurrent Neural Networks

Sequential Models

  • Supervised Sequence Labelling with Recurrent Neural Networks

ToolKits

  • AllenNLP
  • Semantics
  • spaCy
  • Wit.ai extracting named entities
  • Duckling parses text into structured data.