We discuss a general formulation for the Continual Learning (CL) problem for classification—
a learning task where a stream provides samples to a learner and the goal of the learner …

We propose a general, yet simple patch that can be applied to existing regularization-based
continual learning methods called classifier-projection regularization (CPR). Inspired by …

Continual Learning (CL) aims to sequentially train models on streams of incoming data that
vary in distribution by preserving previous knowledge while adapting to new data. Current …

Abstract Current evaluations of Continual Learning (CL) methods typically assume that there
is no constraint on training time and computation. This is an unrealistic assumption for any …

As neural networks are increasingly being applied to real-world applications, mechanisms to
address distributional shift and sequential task learning without forgetting are critical …

The goal of continual learning is to improve the performance of recognition models in
learning sequentially arrived data. Although most existing works are established on the …

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 …

Existing literature in Continual Learning (CL) has focused on overcoming catastrophic
forgetting, the inability of the learner to recall how to perform tasks observed in the past …

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 …

Existing continual learning techniques focus on either task incremental learning (TIL) or
class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the …