Uncertainty Estimation: Not So Bayes-ic

Modelling Uncertainty in Neural Networks.

Project Description:

This was our final project for Simon Lacoste-Julien’s class Probabilistic Graphical Models during Fall 2021.

In this project we provide our own implementation of an approach towards modeling uncertainty in neural networks as proposed in the paper Weight Uncertainty in Neural Networks.

Project Poster:

You can take a look at our project poster here for a quick summary of our results. It’s available in both landscape (scroll down) and portrait PDF format.

Portrait: (Direct Link Here)

This browser does not support PDFs. Please download the PDF to view it: Download PDF.

</embed>



Landscape: (Direct Link Here)

This browser does not support PDFs. Please download the PDF to view it: Download PDF.

</embed>

Github Repo:

And you can check out the code here:

https://github.com/MikeS96/bayesbb

GitHub - MikeS96/bayesbb: Implementation of Bayes By Backprop - PGM Fall 21

Implementation of Bayes By Backprop - PGM Fall 21. Contribute to MikeS96/bayesbb development by creating an account on GitHub.

Project Report:

And a report coming soon! Stay tuned :P