GMvandeVen/continual-learning
A PyTorch research repository implementing continual learning algorithms for training deep neural networks across sequential tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides PyTorch implementations of various continual learning algorithms including XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, and Generative Classifier. It supports experiments in class-incremental, domain-incremental, and task-incremental learning scenarios. The methods address catastrophic forgetting in deep neural networks using techniques such as elastic weight consolidation, generative replay, gradient episodic memory, and variational autoencoders.
Frequently asked
- What is GMvandeVen/continual-learning?
- A PyTorch research repository implementing continual learning algorithms for training deep neural networks across sequential tasks.
- Is continual-learning open source?
- Yes — GMvandeVen/continual-learning is open source, released under the MIT license.
- What language is continual-learning written in?
- GMvandeVen/continual-learning is primarily written in Jupyter Notebook.
- How popular is continual-learning?
- GMvandeVen/continual-learning has 1.9k stars on GitHub.
- Where can I find continual-learning?
- GMvandeVen/continual-learning is on GitHub at https://github.com/GMvandeVen/continual-learning.