Index of content:
Volume 119, Issue 22, 08 December 2003
119(2003); http://dx.doi.org/10.1063/1.1630951View Description Hide Description
Despite their success, the results of first-principles quantum mechanical calculations contain inherent numerical errors caused by various intrinsic approximations. We propose here a neural-network-based algorithm to greatly reduce these inherent errors. As a demonstration, this combined quantum mechanical calculation and neural-network correction approach is applied to the evaluation of standard heat of formation for 180 small- to medium-sized organic molecules at 298 K. A dramatic reduction of numerical errors is clearly shown with systematic deviation being eliminated. For example, the root-mean-square deviation of the calculated for the 180 molecules is reduced from 21.4 to for and from 12.0 to for before and after the neural-network correction.