Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in
adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting …
adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting …
Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning Perspective
Deep neural networks suffer from catastrophic forgetting when continually learning new
concepts. In this paper, we analyze this problem from a data imbalance point of view. We …
concepts. In this paper, we analyze this problem from a data imbalance point of view. We …
CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task
where models are required to continuously learn novel concepts with only a few training …
where models are required to continuously learn novel concepts with only a few training …
A Continual Learning Approach for Failure Prediction Under Non-Stationary Conditions: Application to Condition Monitoring Data Streams
MA Benatia, M HAFSI, S Ben Ayed - Available at SSRN 4868666 - papers.ssrn.com
Accurate estimation of the remaining useful life (RUL) of critical assets plays a pivotal role in
predictive maintenance strategies. Traditional RUL estimation approaches often face …
predictive maintenance strategies. Traditional RUL estimation approaches often face …