This repository contains an implementation of natural continual learning (NCL) for recurrent networks develop in the following paper:
@inproceedings{
kao2021natural,
title = {Natural continual learning: success is a journey, not (just) a destination},
author = {Ta-Chu Kao and Kristopher T Jensen and Gido Martijn van de Ven and Alberto Bernacchia and Guillaume Hennequin},
booktitle = {Thirty-Fifth Conference on Neural Information Processing Systems},
year = {2021},
url = {https://openreview.net/forum?id=W9250bXDgpK}
}
The experiments in feedforward networks were implemented in a fork of the following repository and will be released shortly at this link.
Please feel free to reach out to any of the NCL authors, if you would like access to our feedforward implementation before the public release.
< 635B div class="markdown-heading" dir="auto">