Image Classification using Fuzzy Pooling in Convolutional Kolmogorov-Arnold Networks

TL;DR

This paper introduces a novel CNN architecture that combines Kolmogorov-Arnold Networks and Fuzzy Pooling to enhance interpretability and accuracy in image classification tasks.

Contribution

The paper presents an innovative integration of KAN and Fuzzy Pooling into CNNs, improving interpretability and uncertainty handling in image classification.

Findings

Achieves comparable or higher accuracy than traditional CNNs.

Demonstrates the effectiveness of fuzzy logic in deep learning.

Highlights improved interpretability of the model.

Abstract

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.