Autoencoder–Based Image Representation Learning with Kolmogorov–Arnold Networks

Autoencoders are widely used for learning compact latent representations of images. While convolutional architectures dominate this area due to their ability to exploit spatial locality, recent developments in neural network design have introduced Kolmogorov–Arnold networks (KANs), which replace fix...

Cijeli opis

Bibliografski detalji

Glavni autori:	Urbaniak Ilona Anna, Wieczorek Sylwester, Kołodziej Joanna
Format:	Artigo
Jezik:	Inglês
Izdano:	Sciendo 2026-06-01
Serija:	International Journal of Applied Mathematics and Computer Science
Teme:	autoencoders representation learning kolmogorov–arnold networks fastkan image reconstruction ssim psnr
Online pristup:	https://doi.org/10.61822/amcs-2026-0019
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!