Deep neural networks achieve state-of-the-art and sometimes super-human performance
across a variety of domains. However, when learning tasks sequentially, the networks easily …

Continual learning requires the model to learn multiple tasks sequentially. In continual
learning the model should possess the ability to maintain its performance on old tasks …

In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

Deep network architectures struggle to continually learn new tasks without forgetting the
previous tasks. A recent trend indicates that dynamic architectures based on an expansion …

The goal of continual learning (CL) is to continuously learn new tasks without forgetting
previously learned old tasks. To alleviate catastrophic forgetting, gradient projection based …

Coreset is a small set that provides a data summary for a large dataset, such that training
solely on the small set achieves competitive performance compared with a large dataset. In …

Continual learning is a learning paradigm that learns tasks sequentially with resources
constraints, in which the key challenge is stability-plasticity dilemma, ie, it is uneasy to …

Continual learning algorithms which keep the parameters of new tasks close to that of
previous tasks, are popular in preventing catastrophic forgetting in sequential task learning …

While recent continual learning methods largely alleviate the catastrophic problem on toy-
sized datasets, some issues remain to be tackled to apply them to real-world problem …

Abstract Task-Free Continual Learning (TFCL) aims to learn new concepts from a stream of
data without any task information. The Dynamic Expansion Model (DEM) has shown …