shahariel/TEAL

TEAL: New Selection Strategy for Small Buffers in Experience Replay Class Incremental Learning

14
/ 100
Experimental

This project helps machine learning researchers improve how models learn new information over time without forgetting old knowledge. It takes a stream of data representing new tasks and selects the most important examples to remember, producing a more accurate and stable model. This is especially useful for researchers working with continual learning scenarios, where models need to adapt to evolving datasets.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner working on continual learning problems and need a better strategy for managing memory buffers to prevent 'catastrophic forgetting.'

Not ideal if you are looking for a general-purpose machine learning library or if your primary focus is not on continual learning or experience replay optimization.

continual-learning machine-learning-research deep-learning model-optimization catastrophic-forgetting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

17

Forks

Language

Python

License

Last pushed

Jan 21, 2025

Commits (30d)

0

Get this data via API

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

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