{"ID":2897254,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06417","arxiv_id":"2507.06417","title":"Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification","abstract":"This study conducts a comprehensive comparison of four neural network architectures: Convolutional Neural Network, Capsule Network, Convolutional Kolmogorov-Arnold Network, and the newly proposed Capsule-Convolutional Kolmogorov-Arnold Network. The proposed Capsule-ConvKAN architecture combines the dynamic routing and spatial hierarchy capabilities of Capsule Network with the flexible and interpretable function approximation of Convolutional Kolmogorov-Arnold Networks. This novel hybrid model was developed to improve feature representation and classification accuracy, particularly in challenging real-world biomedical image data. The architectures were evaluated on a histopathological image dataset, where Capsule-ConvKAN achieved the highest classification performance with an accuracy of 91.21%. The results demonstrate the potential of the newly introduced Capsule-ConvKAN in capturing spatial patterns, managing complex features, and addressing the limitations of traditional convolutional models in medical image classification.","short_abstract":"This study conducts a comprehensive comparison of four neural network architectures: Convolutional Neural Network, Capsule Network, Convolutional Kolmogorov-Arnold Network, and the newly proposed Capsule-Convolutional Kolmogorov-Arnold Network. The proposed Capsule-ConvKAN architecture combines the dynamic routing and...","url_abs":"https://arxiv.org/abs/2507.06417","url_pdf":"https://arxiv.org/pdf/2507.06417v2","authors":"[\"Laura Pituková\",\"Peter Sinčák\",\"László József Kovács\",\"Peng Wang\"]","published":"2025-07-08T21:51:05Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}