GMvandeVen/continual-learning

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

56
/ 100
Established

This project helps machine learning researchers and practitioners evaluate and compare different continual learning strategies for deep neural networks. It takes various classification datasets, split into sequential 'contexts' or 'tasks', and applies different continual learning methods. The output includes performance metrics and visualizations that show how well a model learns new information without forgetting previously learned knowledge.

1,832 stars.

Use this if you are a machine learning researcher or engineer interested in experimenting with and comparing various continual learning algorithms for classification tasks.

Not ideal if you need a pre-built solution for a specific real-world application or are not familiar with deep learning experimental setups.

continual-learning deep-learning-research machine-learning-experiments catastrophic-forgetting neural-network-training
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,832

Forks

345

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GMvandeVen/continual-learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.