ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Forklarlig Variational Autoencoder

En Forklarlig Variational Autoencoder (XVAE) udvider det standard VAE-framework med teknikker, der gør dens latente rum fortolkeligt: ved at adskille latente dimensioner, så hver svarer til en menneskeligt forståelig faktor, eller ved hjælp af post-hoc-attributionsmetoder (SHAP, integrerede gradienter), der sporer rekonstruktioner tilbage til input-features. Den bevarer VAE'ens generative kraft, samtidig med at den tilføjer den gennemsigtighed, der kræves i videnskabelige og højrisiko-applikationer.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

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

Kilder

  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

Sådan citerer du denne side

ScholarGate. (2026, June 3). Explainable Variational Autoencoder (XVAE / Interpretable VAE). ScholarGate. https://scholargate.app/da/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

Refereret af

ScholarGateExplainable Variational Autoencoder (Explainable Variational Autoencoder (XVAE / Interpretable VAE)). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/explainable-variational-autoencoder · Datasæt: https://doi.org/10.5281/zenodo.20539026