bayes-nn

by sjchoi86

sjchoi86 /bayes-nn

Lecture notes on Bayesian deep learning

431 Stars 105 Forks Last release: Not found 9 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

Understanding Bayesian Deep Learning

1. Elementary mathematics

  • Set theory
  • Measure theory
  • Probability
  • Random variable
  • Random process
  • Functional analysis (harmonic analysis)

2. Gaussian process

  • Gaussian process
  • Weight-space view
  • Function-space view
  • Gaussian process latent variable model

3. Bayesian neural netwrok

  • Minimum description length
  • Ensemble learning in Bayesian neural network
  • Practical variational inference
  • Bayes by backprop
  • Summary of variational inference
  • Dropout as a Bayesian approximation
  • Stein variational gradient descent

4. Summary

  • Measure thoery
  • Probability
  • Random variable
  • Random process
  • Gaussian process
  • Functional Analysis
  • Summary of variational inference
  • Stein variational gradient descent

5. Uncertainty in Deep Learning

  • Yarin Gal, Uncertainty in Deep Learning
  • Anonymous, Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
  • Patrick McClure, Representing Inferential Uncertainty in Deep Neural Networks through Sampling
  • Balaji Lakshminarayanan, Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
  • Alex Kendal, What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
  • Gregory Kahn, Uncertainty-Aware Reinforcement Learning for Collision Avoidance
  • Charles Richter, Safe Visual Navigation via Deep Learning and Novelty Detection
  • Sungjoon Choi, Uncertainty-Aware Learning from Demonstration Using Mixture Density Networks with Sampling-Free Variance Modeling

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.