sahagobinda/SGP

Official [AAAI] Code Repository for "Continual Learning with Scaled Gradient Projection".

27
/ 100
Experimental

This project helps machine learning researchers and practitioners overcome "catastrophic forgetting" in neural networks. When a model is trained on new tasks sequentially, it often forgets what it learned previously. This method takes existing neural network models and training data for new tasks, then optimizes the learning process to retain knowledge from past tasks while efficiently learning new information. It's designed for those developing or deploying AI models that need to adapt continuously to new data or environments.

No commits in the last 6 months.

Use this if you are building or training neural networks for applications like image classification or reinforcement learning where the model needs to learn new tasks over time without forgetting previously learned knowledge.

Not ideal if you are working with models that are trained once on a static dataset and do not require sequential adaptation or learning new tasks.

continual-learning neural-networks machine-learning-research ai-model-training reinforcement-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Python

License

MIT

Last pushed

Jun 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sahagobinda/SGP"

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