Prediction of potential well's ground state energy using back propagation neural network.

Autor:	Handayana, I. Gusti Ngurah Yudi, Sudiarta, I. Wayan, Marzuki, Afgoni, Annur
Předmět:	GROUND state energy BACK propagation POTENTIAL well MACHINE learning ENERGY consumption
Zdroj:	AIP Conference Proceedings; 2023, Vol. 2619 Issue 1, p1-5, 5p
Abstrakt:	This study aims to build a Machine Learning Back Propagation Neural Network (BPNN) model to solve the Schrodinger equation for the case of potential wells. The input data is the coefficient of the Fourier representation of the well potential, and the output data is the ground state energy. The Neural Network architecture consists of 5 layers (one input layer, three hidden layers, and one output layer) and eight neuron for each layer. The training results, with 74,089 data, showed the ML model to predict the ground state energy of potential wells with an accuracy of 0.9878. [ABSTRACT FROM AUTHOR]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu