- Notifications
You must be signed in to change notification settings - Fork1
Tutorial and discussion on Importance Weighted Autoencoder (IWAE) / Variational Autoencoder (VAE) implementation on MNIST using Tensorflow 2.0
License
NotificationsYou must be signed in to change notification settings
Gabriel-Macias/iwae_tutorial
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
The jupyter notebook included in this repository covers an implementation of Importance Weighted Autoencoders (IWAE) as detailed inhttps://arxiv.org/abs/1509.00519.
The implementation is done inTensorflow 2.1.0 and tested on the binarizedMNIST dataset.
The following theoretical and experimental explorations are covered in this implementation:
- Theory behind IWAE
- Choice of initialization strategy
- Representation learning capabilities of IWAE
- Effect of tighter IWAE bounds
- Large-scale IWAE bound performance
About
Tutorial and discussion on Importance Weighted Autoencoder (IWAE) / Variational Autoencoder (VAE) implementation on MNIST using Tensorflow 2.0
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
No releases published
Packages0
No packages published