Incremental learning approach using fuzzy logic to mitigate catastrophic forgetting

Livia de Souza Alexandre

Track: Full Paper

Abstract:

In this work, we propose a novel approach that combines Elastic Weight Consoli-
dation (EWC) with fuzzy reasoning to address catastrophic forgetting in continual
learning scenarios. The EWC-Fuzzy approach mitigates the challenge of forgetting
previously learned knowledge while enabling the model to adapt to new tasks by
balancing neural network weight regularization with fuzzy rule adaptation. Initially,
the model learns from the first task without EWC regularization, allowing for stan-
dard backpropagation-based learning. For subsequent tasks, EWC is introduced
to prevent significant parameter changes in the neural network that are critical for
previous tasks. Meanwhile, the fuzzy rule parameters—such as the centers, widths,
and outputs—dynamically evolve according to the new data without EWC regula-
rization, allowing them to self-organize in response to the data distribution. This
dual mechanism ensures that model preserves learned knowledge while remaining
flexible and adaptable in the face of new tasks. Our approach addresses the gap in
current research, which often treats EWC and fuzzy reasoning independently. By
integrating these techniques, we provide a promising solution to the challenge of
catastrophic forgetting and enhance the model’s adaptability in dynamic environ-
ments. This study lays the groundwork for further exploration into the fusion of
EWC and fuzzy systems in continual learning.

Submission Number: 38