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....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Entropy (Basel, Switzerland) Ročník 23; číslo 12; s. 1640
Hlavní autoři: Zacherl, Johannes, Frank, Philipp, Enßlin, Torsten A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Switzerland MDPI AG 06.12.2021
MDPI
Témata:
Approximation
Coders
Cross correlation
deep generative network
Fisher information
Fisher information metric
Machine learning
Neural networks
Probability distribution
Random variables
Uncertainty
variational autoencoder
variational methods
variational methods
Fisher information metric
deep generative network
machine learning
variational autoencoder
ISSN:1099-4300, 1099-4300
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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. In particular, the so-called encoder network, the first part of the VAE, which maps its input onto a position in latent space, additionally provides uncertainty information in terms of variance around this position. In this work, an extension to the autoencoder architecture is introduced, the FisherNet. In this architecture, the latent space uncertainty is not generated using an additional information channel in the encoder but derived from the decoder by means of the Fisher information metric. This architecture has advantages from a theoretical point of view as it provides a direct uncertainty quantification derived from the model and also accounts for uncertainty cross-correlations. We can show experimentally that the FisherNet produces more accurate data reconstructions than a comparable VAE and its learning performance also apparently scales better with the number of latent space dimensions.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1099-4300
1099-4300
DOI:10.3390/e23121640