Auto-Encoding Variational Bayes
Cambridge Explorations in Arts and Sciences · 2024
DOI: 10.61603/ceas.v2i1.33 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cambridge Explorations in Arts and Sciences, 2024. Verfasst von Yankun Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 111-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
This paper employs the Auto-Encoding Variational Bayes (AEVB) estimator based on Stochastic Gradient Variational Bayes (SGVB), designed to optimize recognition models for challenging posterior distributions and large-scale datasets. It has been applied to the mnist dataset and extended to form a Dynamic Bayesian Network (DBN) in the context of time series. The paper delves into Bayesian inference, variational methods, and the fusion of Variational Autoencoders (VAEs) and variational techniques. Emphasis is placed on reparameterization for achieving efficient optimization. AEVB employs VAEs as an approximation for intricate posterior distributions.
Zitieren
APA
Chen, Y., Liu, J., Peng, L., Wu, Y., Xu, Y., & Zhang, Z. (2024). Auto-Encoding Variational Bayes. Cambridge Explorations in Arts and Sciences. https://doi.org/10.61603/ceas.v2i1.33
Vancouver
Chen Y, Liu J, Peng L, Wu Y, Xu Y, Zhang Z. Auto-Encoding Variational Bayes. Cambridge Explorations in Arts and Sciences. 2024. doi:10.61603/ceas.v2i1.33
BibTeX
@article{Chen2024,
author = {Chen, Yankun and Liu, Jingxuan and Peng, Lingyun and Wu, Yiqi and Xu, Yige and Zhang, Zhanhao},
title = {Auto-Encoding Variational Bayes},
journal = {Cambridge Explorations in Arts and Sciences},
year = {2024},
doi = {10.61603/ceas.v2i1.33}
}
EUVIMED