This is an unofficial PyTorch implementation of the continual learning experiments described in the following paper:

• https://arxiv.org/abs/1902.06494

https://www.overleaf.com/read/cghtkvkvhmnj

• implement prior- and likelihood-focused continual learning approaches, in particular VCL+coresets and VGR models
• test models permuted MNIST, split MNIST
• compare results

• Alexey Topolnitskiy
• Alsu Sagirova

To install all required packages, run the following command:

pip install -r requirements.txt

To run the experiments you can use IPython notebooks from the notebooks folder