Convolutional Kolmogorov-Arnold Networks

In this paper, we introduce the Convolutional <PRE_TAG>Kolmogorov-Arnold Networks</POST_TAG> (Convolutional <PRE_TAG>KANs</POST_TAG>), 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 <PRE_TAG>KANs</POST_TAG> against traditional architectures across MNIST and Fashion-<PRE_TAG>MNIST</POST_TAG> benchmarks, illustrating that this new approach maintains a similar level of accuracy while using half the amount of parameters. This significant reduction of parameters opens up a new approach to advance the optimization of neural network architectures.