Cargando…
Aesthetics and neural network image representations
We analyze the spaces of images encoded by generative neural networks of the BigGAN architecture. We find that generic multiplicative perturbations of neural network parameters away from the photo-realistic point often lead to networks generating images which appear as “artistic renditions” of the c...
Autor principal: | Janik, Romuald A. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10349859/ https://www.ncbi.nlm.nih.gov/pubmed/37454170 http://dx.doi.org/10.1038/s41598-023-38443-9 |
Ejemplares similares
-
Editorial: Sonification, aesthetic representation of physical quantities
por: Minciacchi, Diego, et al.
Publicado: (2023) -
Is Aesthetic Good? A Study on the Aesthetic and Vitality Judgment of Pictorial Representations of the Dead, Saints and Non-Saints
por: Schieppati, Sara Valentina, et al.
Publicado: (2022) -
Aesthetic experience enhances first-person spatial representation
por: Babo-Rebelo, Mariana, et al.
Publicado: (2022) -
Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
por: Bazgir, Omid, et al.
Publicado: (2020) -
Aesthetic Characteristics of Dance Based on Few-Shot Learning and Neural Networks
por: Qu, Dixin
Publicado: (2022)