sahagobinda/SGP
Official [AAAI] Code Repository for "Continual Learning with Scaled Gradient Projection".
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.
Stars
16
Forks
1
Language
Python
License
MIT
Category
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.
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.