We show that the visible sector probability density function of the Riemann-Theta Boltzmann machine corresponds to a Gaussian mixture model consisting of an infinite number of component multi-variate Gaussians. The weights of the mixture are given by a discrete multi-variate Gaussian over the hidden state space. This allows us to sample the visible sector density function in a straight-forward manner. Furthermore, we show that the visible sector probability density function possesses an affine transform property, similar to the multi-variate Gaussian density.
Sampling the Riemann-Theta Boltzmann Machine / S. Carrazza, D. Krefl. - In: COMPUTER PHYSICS COMMUNICATIONS. - ISSN 0010-4655. - (2020 Jun 30). [Epub ahead of print] [10.1016/j.cpc.2020.107464]
Sampling the Riemann-Theta Boltzmann Machine
S. Carrazza
;
2020
Abstract
We show that the visible sector probability density function of the Riemann-Theta Boltzmann machine corresponds to a Gaussian mixture model consisting of an infinite number of component multi-variate Gaussians. The weights of the mixture are given by a discrete multi-variate Gaussian over the hidden state space. This allows us to sample the visible sector density function in a straight-forward manner. Furthermore, we show that the visible sector probability density function possesses an affine transform property, similar to the multi-variate Gaussian density.File | Dimensione | Formato | |
---|---|---|---|
RTBMsampling.pdf
Open Access dal 01/07/2022
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
495.01 kB
Formato
Adobe PDF
|
495.01 kB | Adobe PDF | Visualizza/Apri |
1-s2.0-S0010465520302174-main.pdf
Open Access dal 01/07/2022
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
697.42 kB
Formato
Adobe PDF
|
697.42 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.