BurakGurbuz97/NICE
NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning
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.
Stars
27
Forks
1
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.