Numerical solution of the Schrödinger equation by neural network and genetic algorithm

Abstract A new approach for solving the Schrodinger equation based on genetic algorithm (GA) and artificial neural network (NN) is presented. Feed-forward perceptron-type network is used to represent the wavefunction, while network parameters are optimized by micro-genetic algorithm so that the NN satisfies the Schrodinger equation. In the GA breeding process, random point evaluation method (RPEM) for fitness evaluation is introduced to improve the convergence. Final solution is obtained by invoking deterministic optimizer which corresponds to a “learning process” of the NN. The present method is tested in the calculation of one-dimensional harmonic oscillator and other model potentials.

[1]  Numerical solutions of the Schrödinger equation directly or perturbatively by a genetic algorithm: test cases , 1998 .

[2]  Donald F. Weaver,et al.  Three variations of genetic algorithm for searching biomolecular conformation space: Comparison of GAP 1.0, 2.0, and 3.0 , 1999 .

[3]  Bernd Hartke.  Global geometry optimization of clusters using a growth strategy optimized by a genetic algorithm , 1995 .

[4]  Pinaki Chaudhury,et al.  Locating critical points on multi-dimensional surfaces by genetic algorithm: test cases including normal and perturbed argon clusters , 1999 .

[5]  Harold A. Scheraga,et al.  Description of the potential energy surface of the water dimer with an artificial neural network , 1997 .

[6]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[7]  Bernd Hartke,et al.  Global geometry optimization of (Ar)n and B(Ar)n clusters using a modified genetic algorithm , 1996 .

[8]  D. Fotiadis,et al.  Artificial neural network methods in quantum mechanics , 1997, quant-ph/9705029.

[9]  Howard R. Mayne,et al.  Global geometry optimization of atomic clusters using a modified genetic algorithm in space‐fixed coordinates , 1996 .

[10]  Antônio de Pádua Braga,et al.  Artificial neural network applied for predicting rainbow trajectories in atomic and molecular classical collisions , 1997 .

[11]  Bobby G. Sumpter,et al.  A neural network approach to the study of internal energy flow in molecular systems , 1992 .

[12]  Yehuda Zeiri,et al.  Application of genetic algorithm to the calculation of bound states and local density approximations , 1995 .

[13]  Juan C. Meza,et al.  A comparison of a direct search method and a genetic algorithm for conformational searching , 1996 .

[14]  J. Gunn.  Sampling protein conformations using segment libraries and a genetic algorithm , 1997 .

[15]  Bjarne Amstrup,et al.  Genetic Algorithm with Migration on Topology Conserving Maps for Optimal Control of Quantum Systems , 1995 .

[16]  D. Frederick,et al.  Developments in theoretical and applied mechanics , 1963 .

[17]  Bobby G. Sumpter,et al.  Theory and Applications of Neural Computing in Chemical Science , 1994 .

[18]  Yong L. Xiao,et al.  Genetic algorithm: a new approach to the prediction of the structure of molecular clusters , 1993 .

[19]  K. Ho,et al.  Structural optimization of Lennard-Jones clusters by a genetic algorithm , 1996 .

[20]  L. Kułak,et al.  Neural network solution of the Schrödinger equation for a two-dimensional harmonic oscillator , 1993 .

[21]  Steven D. Brown,et al.  Neural network models of potential energy surfaces , 1995 .

[22]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[23]  Michihiko Sugawara,et al.  NUMERICAL SOLUTION OF THE SCHRODINGER EQUATION BY A MICROGENETIC ALGORITHM , 2000 .

[24]  Howard R. Mayne,et al.  A study of genetic algorithm approaches to global geometry optimization of aromatic hydrocarbon microclusters , 1998 .

[25]  P. Brumer,et al.  A genetic algorithm approach to fitting polyatomic spectra via geometry shifts , 1996 .