Variational autoencoders are deep generative models that have recently received a great deal of attention due to their ability to model the latent distribution of any kind of input such as images and audio signals, among others. A novel variational autoncoder in the quaternion domain H, namely the QVAE, has been recently proposed, leveraging the augmented second order statics of H-proper signals. In this paper, we analyze the QVAE under an information-theoretic perspective, studying the ability of the H-proper model to approximate improper distributions as well as the built-in H-proper ones and the loss of entropy due to the improperness of the input signal. We conduct experiments on a substantial set of quaternion signals, for each of which the QVAE shows the ability of modelling the input distribution, while learning the improperness and increasing the entropy of the latent space. The proposed analysis will prove that proper QVAEs can be employed with a good approximation even when the quaternion input data are improper.

An information-theoretic perspective on proper quaternion variational autoencoders / Grassucci, E.; Comminiello, D.; Uncini, A.. - In: ENTROPY. - ISSN 1099-4300. - 23:7(2021), pp. 1-17. [10.3390/e23070856]

An information-theoretic perspective on proper quaternion variational autoencoders

Grassucci E.
;
Comminiello D.;Uncini A.
2021

Abstract

Variational autoencoders are deep generative models that have recently received a great deal of attention due to their ability to model the latent distribution of any kind of input such as images and audio signals, among others. A novel variational autoncoder in the quaternion domain H, namely the QVAE, has been recently proposed, leveraging the augmented second order statics of H-proper signals. In this paper, we analyze the QVAE under an information-theoretic perspective, studying the ability of the H-proper model to approximate improper distributions as well as the built-in H-proper ones and the loss of entropy due to the improperness of the input signal. We conduct experiments on a substantial set of quaternion signals, for each of which the QVAE shows the ability of modelling the input distribution, while learning the improperness and increasing the entropy of the latent space. The proposed analysis will prove that proper QVAEs can be employed with a good approximation even when the quaternion input data are improper.
2021
generative learning; properness; quaternion neural networks; second-order circularity; variational autoencoder
01 Pubblicazione su rivista::01a Articolo in rivista
An information-theoretic perspective on proper quaternion variational autoencoders / Grassucci, E.; Comminiello, D.; Uncini, A.. - In: ENTROPY. - ISSN 1099-4300. - 23:7(2021), pp. 1-17. [10.3390/e23070856]
File allegati a questo prodotto
File Dimensione Formato  
Grassucci_Information-Theoretic_2021.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 3.25 MB
Formato Adobe PDF
3.25 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1606334
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 7
social impact