In this work, we propose a novel approach that combines Elastic Weight Consoli-dation (EWC) with fuzzy reasoning to address catastrophic forgetting in continuallearning scenarios. The EWC-Fuzzy approach mitigates the challenge of forgettingpreviously learned knowledge while enabling the model to adapt to new tasks bybalancing 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 introducedto prevent significant parameter changes in the neural network that are critical forprevious 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. Thisdual mechanism ensures that model preserves learned knowledge while remainingflexible and adaptable in the face of new tasks. Our approach addresses the gap incurrent research, which often treats EWC and fuzzy reasoning independently. Byintegrating these techniques, we provide a promising solution to the challenge ofcatastrophic forgetting and enhance the model’s adaptability in dynamic environ-ments. This study lays the groundwork for further exploration into the fusion ofEWC and fuzzy systems in continual learning.