Skip to content

Using Neuro Evolution to train and architecture-search for Bayesian Neural Networks

Notifications You must be signed in to change notification settings

AlbertoCastelo/Neuro-Evolution-BNN

Repository files navigation

Neuroevolution of Bayesian Neural Networks

Using Neuro Evolution to train and architecture-search in Bayesian Neural Networks (Feed-forward) for Supervised Learning tasks: Regression and Classification.

Networks are implemented in Pytorch and can run both in CPU and GPU.

Report: Neuroevolution of Bayesian Neural Networks

Make commands

Spin up environment

make jupyter

Run test

make test

Run Experiments

Different datasets are available.

Neuroevolution

Check examples folder to run Neuro-evolution of Bayesian Neural Networks

Standard Deep Learning

Check deep_learning folder to run both:

  • Frequentist Networks trained by backpropagation
  • Bayesian Networks trained by backpropagation

About

Using Neuro Evolution to train and architecture-search for Bayesian Neural Networks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published