5 results found Sort:
- Filter by Primary Language:
- Python (4)
- Jupyter Notebook (1)
- +
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.
icarl
replay
distillation
deep-learning
generative-models
lifelong-learning
continual-learning
incremental-learning
replay-through-feedback
variational-autoencoder
gradient-episodic-memory
task-incremental-learning
artificial-neural-networks
class-incremental-learning
domain-incremental-learning
elastic-weight-consolidation
Created
2018-09-26
41 commits to master branch, last one 8 months ago
Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.
Created
2021-04-20
192 commits to main branch, last one 9 months ago
A brain-inspired version of generative replay for continual learning with deep neural networks (e.g., class-incremental learning on CIFAR-100; PyTorch code).
replay
split-mnist
distillation
deep-learning
brain-inspired
permuted-mnist
split-cifar100
internal-replay
generative-replay
lifelong-learning
continual-learning
incremental-learning
synaptic-intelligence
replay-through-feedback
variational-autoencoder
artificial-neural-networks
elastic-weight-consolidation
Created
2020-08-04
10 commits to master branch, last one 3 years ago
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 classifi...
hat
icarl
tpami
packnet
framework
inaturalist
tinyimagenet
deep-learning
defy-forgetting
neural-networks
continual-learning
classification-tasks
incremental-learning
hyperparameter-tuning
memory-aware-synapses
synaptic-intelligence
gradient-episodic-memory
incremental-moment-matching
elastic-weight-consolidation
Created
2020-04-06
6 commits to master branch, last one 3 years ago
PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).
Created
2021-04-20
12 commits to main branch, last one about a year ago