DocumentCode
2351752
Title
Artificial neural networks applied to theoretical chemistry
Author
de Almeida, M.B. ; Belchior, J.C. ; Braga, J.P. ; Braga, A.P.
Author_Institution
Dept. de Engenharia Eletronica, Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil
fYear
1998
fDate
9-11 Dec 1998
Firstpage
232
Lastpage
234
Abstract
Artificial neural networks are used to invert the potential energy function for diatomic molecules. The latter was based on radial basis function technique. Fifteen diatomic systems were used and leave-three-out for testing the learning procedure. The relative average error of the inverted potential compared against the exact one is about 5% which is considered to be satisfactory
Keywords
DIM calculations; chemistry computing; neural nets; potential energy functions; chemistry; diatomic molecules; neural networks; potential energy function inversion; radial basis function technique; Artificial neural networks; Chemistry; Cost function; Equations; Neural networks; Particle scattering; Performance evaluation; Potential energy; Quantum mechanics; System testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1998. Proceedings. Vth Brazilian Symposium on
Conference_Location
Belo Horizonte
Print_ISBN
0-8186-8629-4
Type
conf
DOI
10.1109/SBRN.1998.731036
Filename
731036
Link To Document