Cargando…
Hyperrealistic neural decoding for reconstructing faces from fMRI activations via the GAN latent space
Neural decoding can be conceptualized as the problem of mapping brain responses back to sensory stimuli via a feature space. We introduce (i) a novel experimental paradigm that uses well-controlled yet highly naturalistic stimuli with a priori known feature representations and (ii) an implementation...
Autores principales: | Dado, Thirza, Güçlütürk, Yağmur, Ambrogioni, Luca, Ras, Gabriëlle, Bosch, Sander, van Gerven, Marcel, Güçlü, Umut |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8741893/ https://www.ncbi.nlm.nih.gov/pubmed/34997012 http://dx.doi.org/10.1038/s41598-021-03938-w |
Ejemplares similares
-
Brain2Pix: Fully convolutional naturalistic video frame reconstruction from brain activity
por: Le, Lynn, et al.
Publicado: (2022) -
Representations of naturalistic stimulus complexity in early and associative visual and auditory cortices
por: Güçlütürk, Yağmur, et al.
Publicado: (2018) -
Explainable and interpretable models in computer vision and machine learning
por: Escalante, Hugo Jair, et al.
Publicado: (2019) -
End-to-end neural system identification with neural information flow
por: Seeliger, K., et al.
Publicado: (2021) -
Disentangling the latent space of GANs for semantic face editing
por: Niu, Yongjie, et al.
Publicado: (2023)