We introduce a new neural network-based continual learning algorithm, dubbed as
Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian …

Continual learning tackles the setting of learning different tasks sequentially. Despite the lots
of previous solutions, most of them still suffer significant forgetting or expensive memory …

We propose a novel regularization-based continual learning method, dubbed as Adaptive
Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based …

Continual learning aims to learn new tasks without forgetting previously learned ones. This
is especially challenging when one cannot access data from previous tasks and when the …

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the
data distribution during learning. This phenomenon has long been considered a major …

In the continual learning setting, tasks are encountered sequentially. The goal is to learn
whilst i) avoiding catastrophic forgetting, ii) efficiently using model capacity, and iii) …

Continual learning deals with training models on new tasks and datasets in an online
fashion. One strand of research has used probabilistic regularization for continual learning …

Continual learning is a setting where machine learning models learn novel concepts from
continuously shifting training data, while simultaneously avoiding degradation of knowledge …

In contrast to the natural capabilities of humans to learn new tasks in a sequential fashion,
neural networks are known to suffer from catastrophic forgetting, where the model's …