Convolutional Kolmogorov-Arnold Networks

arXiv:2406.13155v1 Announce Type: new
Abstract: In this paper, we introduce the Convolutional Kolmogorov-Arnold Networks (Convolutional KANs), an innovative alternative to the standard Convolutional Neural Networks (CNNs) that have revolutionized the field of computer vision. We integrate the non-linear activation functions presented in Kolmogorov-Arnold Networks (KANs) into convolutions to build a new layer. Throughout the paper, we empirically validate the performance of Convolutional KANs against traditional architectures across MNIST and Fashion-MNIST benchmarks, illustrating that this new approach maintains a similar level …

abstract alternative arxiv build cnns computer computer vision convolutional convolutional neural networks cs.ai cs.cv functions layer linear networks neural networks non-linear paper standard type vision