Image Classification using Fuzzy Pooling in Convolutional Kolmogorov-Arnold Networks
This addresses the problem of interpretability and uncertainty handling in image classification for deep learning practitioners, though it appears incremental as it modifies existing CNN architectures.
The paper tackles the need for interpretable and accurate deep learning by integrating Kolmogorov-Arnold Network (KAN) classification heads and Fuzzy Pooling into CNNs for image classification, achieving comparable or higher accuracy than traditional models.
Nowadays, deep learning models are increasingly required to be both interpretable and highly accurate. We present an approach that integrates Kolmogorov-Arnold Network (KAN) classification heads and Fuzzy Pooling into convolutional neural networks (CNNs). By utilizing the interpretability of KAN and the uncertainty handling capabilities of fuzzy logic, the integration shows potential for improved performance in image classification tasks. Our comparative analysis demonstrates that the modified CNN architecture with KAN and Fuzzy Pooling achieves comparable or higher accuracy than traditional models. The findings highlight the effectiveness of combining fuzzy logic and KAN to develop more interpretable and efficient deep learning models. Future work will aim to expand this approach across larger datasets.