Deep state-space models (DSSMs) have gained popularity in recent years due to their
potent modeling capacity for dynamic systems. However, existing DSSM works are limited to …

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 …

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, ie,
model performance deterioration on past tasks when learning a new task. However, the …

Continual learning (CL) aims to develop techniques by which a single model adapts to an
increasing number of tasks encountered sequentially, thereby potentially leveraging …

Continual learning aims to provide intelligent agents capable of learning multiple tasks
sequentially with neural networks. One of its main challenging, catastrophic forgetting, is …

The goal of Continual Learning (CL) task is to continuously learn multiple new tasks
sequentially while achieving a balance between the plasticity and stability of new and old …

Continual learning aims to learn a series of tasks sequentially without forgetting the
knowledge acquired from the previous ones. In this work, we propose the Hessian Aware …

The goal of continual learning (CL) is to learn different tasks over time. The main desiderata
associated with CL are to maintain performance on older tasks, leverage the latter to …

The continual learning (CL) paradigm aims to enable neural networks to learn tasks
continually in a sequential fashion. The fundamental challenge in this learning paradigm is …

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 …