chrhenning / hypercl
Continual Learning with Hypernetworks. A continual learning approach that has the flexibility to learn a dedicated set of parameters, fine-tuned for every task, that doesn't require an increase in the number of trainable weights and is robust against catastrophic forgetting.
☆163Updated 3 years ago
Alternatives and similar repositories for hypercl:
Users that are interested in hypercl are comparing it to the libraries listed below
- Codebase for "Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning". This is a ServiceNow Research pro…☆105Updated 2 years ago
- Official Code Repository for La-MAML: Look-Ahead Meta-Learning for Continual Learning"☆76Updated 4 years ago
- Official code for ICLR 2020 paper "A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning."☆100Updated 4 years ago
- Overcoming catastrophic forgetting with hard attention to the task☆214Updated 6 years ago
- Code for the NeurIPS19 paper "Meta-Learning Representations for Continual Learning"☆201Updated 8 months ago
- Implementation of the variational continual learning method☆189Updated 5 years ago
- ☆72Updated 2 years ago
- Codebase for "Online Continual Learning with Maximally Interfered Retrieval"☆101Updated 2 years ago
- Continual Hyperparameter Selection Framework. Compares 11 state-of-the-art Lifelong Learning methods and 4 baselines. Official Codebase …☆201Updated 3 years ago
- An implementation of EWC with PyTorch☆249Updated 6 years ago
- Fork of the GEM project (https://github.com/facebookresearch/GradientEpisodicMemory) including Meta-Experience Replay (MER) methods from …☆146Updated 4 years ago
- Package for working with hypernetworks in PyTorch.☆122Updated last year
- Code for "Supermasks in Superposition"☆121Updated last year
- Official [ICLR] Code Repository for "Gradient Projection Memory for Continual Learning"☆90Updated 3 years ago
- ☆38Updated 5 months ago
- Continual Learning in Low-rank Orthogonal Subspaces (NeurIPS'20)☆36Updated 4 years ago
- Code to accompany our paper "Continual Learning Through Synaptic Intelligence" ICML 2017☆102Updated 6 years ago
- Implementation of Bayesian Gradient Descent☆37Updated last year
- Code for "Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent" (ICML 2020 - Lifelong Learning Workshop)☆42Updated 2 years ago
- Towards increasing stability of neural networks for continual learning: https://arxiv.org/abs/2006.06958.pdf (NeurIPS'20)☆75Updated 2 years ago
- Evaluate three types of task shifting with popular continual learning algorithms.☆518Updated 3 years ago
- Coresets via Bilevel Optimization☆65Updated 4 years ago
- ☆53Updated 5 years ago
- PyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017☆162Updated 7 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆120Updated 3 years ago
- Continual Learning in Recurrent Neural Networks☆37Updated 3 years ago
- The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.☆193Updated last year
- Meta-Learning with Warped Gradient Descent☆93Updated 4 years ago
- Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and o…☆291Updated last year
- Official implementation of the Averaged Gradient Episodic Memory (A-GEM) in Tensorflow☆203Updated 3 years ago