Skip to content

Train a simple convnet on the MNIST dataset and evaluate the BALD acquisition function

License

Notifications You must be signed in to change notification settings

xiaorong108/acquisition_example

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

acquisition_example

Train a simple convnet on the MNIST dataset and evaluate the BALD acquisition function

The acquisition function could then be used for active learning with the images the model is most confused about (highest acquisition function value).

See Deep Bayesian Active Learning with Image Data. This code extends on the Keras CNN example.

About

Train a simple convnet on the MNIST dataset and evaluate the BALD acquisition function

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%