Probabilistic Autoencoder Using Fisher Information

Probabilistic Autoencoder Using Fisher Information

Neural networks play a growing role in many scientific disciplines, including physics. Variational autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional latent space, which have a probabilistic interpretation....

Full description

Bibliographic Details
Main Authors: Johannes Zacherl, Philipp Frank, Torsten A. Enßlin
Format: Article
Language:English
Published: MDPI AG 2021-12-01
Series:Entropy
Subjects:
machine learning
Fisher information metric
variational methods
variational autoencoder
deep generative network
Online Access:https://www.mdpi.com/1099-4300/23/12/1640

Internet

https://www.mdpi.com/1099-4300/23/12/1640

Similar Items