In this paper we design and use two Deep Learning models to generate the
ground and excited wavefunctions of different Hamiltonians suitable for the
study the vibrations of molecular systems. The generated neural networks are
trained with Hamiltonians that have analytical solutions, and ask the network
to generalize these solutions to more complex Hamiltonian functions. This
approach allows to reproduce the excited vibrational wavefunctions of different
molecular potentials. All methodologies used here are data-driven, therefore
they do not assume any information about the underlying physical model of the
system. This makes this approach versatile, and can be used in the study of
multiple systems in quantum chemistry.
%0 Generic
%1 domingo2021learning
%A Domingo, Laia
%A Borondo, Florentino
%D 2021
%K neural_network vibrational_states
%T Deep learning methods for the computation of vibrational wavefunctions
%U http://arxiv.org/abs/2103.00202
%X In this paper we design and use two Deep Learning models to generate the
ground and excited wavefunctions of different Hamiltonians suitable for the
study the vibrations of molecular systems. The generated neural networks are
trained with Hamiltonians that have analytical solutions, and ask the network
to generalize these solutions to more complex Hamiltonian functions. This
approach allows to reproduce the excited vibrational wavefunctions of different
molecular potentials. All methodologies used here are data-driven, therefore
they do not assume any information about the underlying physical model of the
system. This makes this approach versatile, and can be used in the study of
multiple systems in quantum chemistry.
@misc{domingo2021learning,
abstract = {In this paper we design and use two Deep Learning models to generate the
ground and excited wavefunctions of different Hamiltonians suitable for the
study the vibrations of molecular systems. The generated neural networks are
trained with Hamiltonians that have analytical solutions, and ask the network
to generalize these solutions to more complex Hamiltonian functions. This
approach allows to reproduce the excited vibrational wavefunctions of different
molecular potentials. All methodologies used here are data-driven, therefore
they do not assume any information about the underlying physical model of the
system. This makes this approach versatile, and can be used in the study of
multiple systems in quantum chemistry.},
added-at = {2021-03-17T09:01:04.000+0100},
author = {Domingo, Laia and Borondo, Florentino},
biburl = {https://www.bibsonomy.org/bibtex/27699f6bac6bc3c9409e68a62f9c67170/flo118},
interhash = {7532c793d23a32b0a367b9bee2e78282},
intrahash = {7699f6bac6bc3c9409e68a62f9c67170},
keywords = {neural_network vibrational_states},
note = {cite arxiv:2103.00202},
timestamp = {2021-03-17T09:01:04.000+0100},
title = {Deep learning methods for the computation of vibrational wavefunctions},
url = {http://arxiv.org/abs/2103.00202},
year = 2021
}