The goal of this contribution is to provide a unique method for simulating and forecasting planetary orbits by utilizing the hypercomplex neural networks (HNN) enhanced performance. The learning technique used by these structures is based on quaternion algebra, which reduces the number of epochs needed to reach an adequate level of approximation and the number of parameters needed to model the dataset. Additionally, we provide a method for anticipating the results of the learning phase by establishing appropriate hypercomplex auxiliary networks to forecast the trends of the network primary weights.
Fast hypercomplex neural networks for modeling Venus planetary orbit
Buscarino A.;Famoso C.;Fortuna L.;Puglisi G.
2023-01-01
Abstract
The goal of this contribution is to provide a unique method for simulating and forecasting planetary orbits by utilizing the hypercomplex neural networks (HNN) enhanced performance. The learning technique used by these structures is based on quaternion algebra, which reduces the number of epochs needed to reach an adequate level of approximation and the number of parameters needed to model the dataset. Additionally, we provide a method for anticipating the results of the learning phase by establishing appropriate hypercomplex auxiliary networks to forecast the trends of the network primary weights.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
