TY - JOUR
T1 - Neural network within a Bayesian inference framework
AU - Gómez-Vargas, Isidro
AU - Esquivel, Ricardo Medel
AU - Garciá-Salcedo, Ricardo
AU - Vázquez, J. Alberto
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
PY - 2021/3/18
Y1 - 2021/3/18
N2 - In Bayesian inference, the likelihood functions are evaluated thousands of times. In this paper we explore the use of an Artificial Neural Network to learn how to calculate the likelihood function and thus speed up the Bayesian inference process. We test the performance of the neural network on a parameter estimation of the standard cosmological model and show that this method can reduce the computational time.
AB - In Bayesian inference, the likelihood functions are evaluated thousands of times. In this paper we explore the use of an Artificial Neural Network to learn how to calculate the likelihood function and thus speed up the Bayesian inference process. We test the performance of the neural network on a parameter estimation of the standard cosmological model and show that this method can reduce the computational time.
UR - http://www.scopus.com/inward/record.url?scp=85103299492&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/1723/1/012022
DO - 10.1088/1742-6596/1723/1/012022
M3 - Artículo de la conferencia
AN - SCOPUS:85103299492
SN - 1742-6588
VL - 1723
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012022
T2 - 10th International Congress of Physics Engineering, CIIF 2020
Y2 - 28 September 2020 through 30 September 2020
ER -