Machine learningDeep learning / NLP / CV

Objašnjivi Varijacijski Autoenkoder

Objašnjivi Varijacijski Autoenkoder (XVAE) proširuje standardni VAE okvir tehnikama koje čine njegov latentni prostor interpretativnim: razdvajanjem latentnih dimenzija tako da svaka odgovara faktoru razumljivom čovjeku, ili post-hoc metodama atribucije (SHAP, integrirani gradijenti) koje prate rekonstrukcije do ulaznih značajki. Zadržava generativnu moć VAE-a dok dodaje transparentnost potrebnu u znanstvenim i visokorizičnim primjenama.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014). link
  2. Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., & Lerchner, A. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In Proceedings of the 5th International Conference on Learning Representations (ICLR 2017). link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Explainable Variational Autoencoder (XVAE / Interpretable VAE). ScholarGate. https://scholargate.app/hr/deep-learning/explainable-variational-autoencoder

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateExplainable Variational Autoencoder (Explainable Variational Autoencoder (XVAE / Interpretable VAE)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/explainable-variational-autoencoder · Skup podataka: https://doi.org/10.5281/zenodo.20539026