AI RESEARCH
KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition
arXiv CS.CV
•
ArXi:2604.23320v1 Announce Type: new The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogoro-Arnold neural networks (KANs), based on the Kolmogoro-Arnold representation theorem, have shown potential to replace Multi-Layer Perceptrons (MLPs) in deep learning. KANs, which use learnable nonlinear activations on edges and simple summation on nodes, offer fewer parameters and greater explainability compared to MLPs.