Replication of existing baselines that address incremental learning issues and definition of new approaches to overcome existing limitations
-
Updated
Aug 2, 2020 - Jupyter Notebook
Replication of existing baselines that address incremental learning issues and definition of new approaches to overcome existing limitations
Reproduction of existing baselines that address incremental learning issues and definition of new approaches to overcome existing limitations
Implementation of several variations of the iCaRL incremental learning algorithm in PyTorch.
The main goal of this project is to implement a neural network capable of learning different tasks without forgetting the ones it has learned before.
Continual Hyperparameter Selection Framework. Compares 11 state-of-the-art Lifelong Learning methods and 4 baselines. Official Codebase of "A continual learning survey: Defying forgetting in classification tasks." in IEEE TPAMI.
Class Incremental Learning (iCaRL, EEIL, BiC) reproduce github repository.
Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
Add a description, image, and links to the icarl topic page so that developers can more easily learn about it.
To associate your repository with the icarl topic, visit your repo's landing page and select "manage topics."