morning-dews / PGMA_tensorflow
Code for Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation
☆21Updated 5 years ago
Related projects: ⓘ
- Official code for ICLR 2020 paper "A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning."☆97Updated 4 years ago
- (NeurIPS 2020) Meta-Consolidation for Continual Learning☆36Updated 3 years ago
- ☆53Updated 4 years ago
- Implementation of Bayesian Gradient Descent☆37Updated 11 months ago
- Codebase for "Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning". This is a ServiceNow Research pro…☆102Updated 2 years ago
- Neat and flexible implementation of MAML in pytorch: https://arxiv.org/abs/1703.03400☆59Updated 3 years ago
- Overcoming Catastrophic Forgetting by Incremental Moment Matching (IMM)☆34Updated 6 years ago
- This repository contains implementations of the paper, Bayesian Model-Agnostic Meta-Learning.☆58Updated 5 years ago
- ☆31Updated last year
- Codebase for "Online Continual Learning with Maximally Interfered Retrieval"☆98Updated last year
- Code accompanying the ICML-2018 paper "Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace"☆39Updated 5 years ago
- ☆27Updated 6 years ago
- NeurIPS 2019 : Learning to Propagate for Graph Meta-Learning☆36Updated 4 years ago
- code for paper "Ju Xu, Zhanxing Zhu. Reinforced Continual Learning. NIPS 2018."☆36Updated 5 years ago
- Official Implementation of "Random Path Selection for Incremental Learning" paper. NeurIPS 2019☆53Updated last year
- Explaining a black-box using Deep Variational Information Bottleneck Approach☆46Updated last year
- Feature-Critic Networks for Heterogeneous Domain Generalisation☆50Updated 5 years ago
- ☆70Updated last year
- ARML for ICLR 2020☆42Updated 4 years ago
- Code for Unsupervised Learning via Meta-Learning.☆120Updated 5 years ago
- Code for the paper "Generalizing to Unseen Domains via Adversarial Data Augmentation", NeurIPS 2018☆121Updated 4 years ago
- The rep for the RotateNetworks in ICPR18, Beijing, China.☆33Updated 6 years ago
- ☆26Updated 4 years ago
- Code for Unsupervised Learning via Meta-Learning.☆65Updated 3 years ago
- ☆13Updated 6 years ago
- Official Code Repository for La-MAML: Look-Ahead Meta-Learning for Continual Learning"☆71Updated 3 years ago
- HSML for ICML 2019☆51Updated 5 years ago
- Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in fu…☆53Updated 3 years ago
- infinite mixture prototypes for few-shot learning☆49Updated last year
- ☆14Updated 5 years ago