Skip to content

Files

bnn-inference

Simple Bayesian Neural Network Example

Key outcome

This example compares the use of Pascal and Pytorch to write a simple Bayesian Neural Network that is trained using variational inference.

The PyTorch code was obtained from saxena-mayur/Weight-Uncertainty-in-Neural-Networks.

Usage

To run this example, run the following from the root directory of this project:

make eg-bnn-simple

Then look inside examples/bnn-simple/plots/ for the plots generated by Pascal and PyTorch. They should look exactly the same.