sahagobinda/GPM
Official [ICLR] Code Repository for "Gradient Projection Memory for Continual Learning"
This project helps machine learning engineers build AI systems that can learn new skills or recognize new types of data without forgetting what they've already learned. It takes in a neural network and a sequence of new data tasks, then trains the network to adapt to the new tasks while preserving its knowledge from previous ones. The result is a more robust AI model capable of continuous adaptation. This is for machine learning practitioners developing AI applications.
No commits in the last 6 months.
Use this if you need to train a neural network incrementally on new datasets or tasks, and you want to prevent the model from 'forgetting' its prior knowledge.
Not ideal if you are training a model from scratch on a single, static dataset, or if your primary concern is not catastrophic forgetting.
Stars
98
Forks
20
Language
Python
License
MIT
Category
Last pushed
Jun 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sahagobinda/GPM"
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.