Regularization-Based Efficient Continual Learning in Deep State-Space Models

arXiv:2403.10123v1 Announce Type: new
Abstract: 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 single-task modeling, which requires retraining with historical task data upon revisiting a forepassed task. To address this limitation, we propose continual learning DSSMs (CLDSSMs), which are capable of adapting to evolving tasks without catastrophic forgetting. Our proposed CLDSSMs integrate mainstream regularization-based continual learning (CL) methods, ensuring efficient updates with …

abstract arxiv capacity continual cs.lg data dynamic however modeling regularization retraining space state systems type