The goal of continual learning is to find a model that solves multiple learning tasks which are
presented sequentially to the learner. A key challenge in this setting is that the learner may" …

In most machine learning algorithms, training data is assumed to be independent and
identically distributed (iid). When it is not the case, the algorithm's performances are …

A growing body of research in continual learning focuses on the catastrophic forgetting
problem. While many attempts have been made to alleviate this problem, the majority of the …

Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant
recent attention. However, most work has focused on the experimental performance of CL …

We formulate the continual learning (CL) problem via dynamic programming and model the
trade-off between catastrophic forgetting and generalization as a two-player sequential …

The ability of a model to learn continually can be empirically assessed in different continual
learning scenarios. Each scenario defines the constraints and the opportunities of the …

In the recent years, lifelong learning (LL) has attracted a great deal of attention in the deep
learning community, where it is often called continual learning. Though it is well-known that …

Standard artificial neural networks suffer from the well-known issue of catastrophic
forgetting, making continual or lifelong learning difficult for machine learning. In recent years …

Continual Learning (CL) algorithms incrementally learn a predictor or representation across
multiple sequentially observed tasks. Designing CL algorithms that perform reliably and …

We study the relationship between catastrophic forgetting and properties of task sequences.
In particular, given a sequence of tasks, we would like to understand which properties of this …