BurakGurbuz97/NICE

NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning

27
/ 100
Experimental

This project helps machine learning practitioners who need their deep neural networks to learn new object categories over time without forgetting previous ones. It allows a neural network to take in new class data sequentially and incrementally add knowledge. The output is a single, continuously learning model that adapts to new information without needing to store or re-process old data.

No commits in the last 6 months.

Use this if you are building AI models that need to adapt and learn new categories continuously from incoming data streams, especially when storing or replaying past data is impractical.

Not ideal if your learning task involves static datasets where all categories are known upfront and there's no need for incremental knowledge acquisition.

continual-learning class-incremental-learning dynamic-data-environments neural-network-adaptation machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

MIT

Last pushed

Jul 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BurakGurbuz97/NICE"

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