Neural-network-assisted genetic algorithm applied to silicon clusters

Recently, a new optimization procedure that combines the power of artificial neural-networks with the versatility of the genetic algorithm (GA) was introduced. This method, called neural-network-assisted genetic algorithm (NAGA), uses a neural network to restrict the search space and it is expected to speed up the solution of global optimization problems if some previous information is available. In this paper, we have tested NAGA to determine the ground-state geometry of Si{sub n} (10{<=}n{<=}15) according to a tight-binding total-energy method. Our results indicate that NAGA was able to find the desired global minimum of the potential energy for all the test cases and it was at least ten times faster than pure genetic algorithm.

[1]  H. Scheraga,et al.  On the multiple-minima problem in the conformational analysis of molecules: deformation of the potential energy hypersurface by the diffusion equation method , 1989 .

[2]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[3]  F. Stillinger,et al.  Nonlinear optimization simplified by hypersurface deformation , 1988 .

[4]  A. Shvartsburg,et al.  Ionization of medium-sized silicon clusters and the geometries of the cations , 1998 .

[5]  Howard R. Mayne,et al.  Minimization of small silicon clusters using the space-fixed modified genetic algorithm method , 1996 .

[6]  Phillips,et al.  Surface and thermodynamic interatomic force fields for silicon clusters and bulk phases. , 1989, Physical review. B, Condensed matter.

[7]  Kolomenskii,et al.  Nonlinear excitation of capillary waves by the Marangoni motion induced with a modulated laser beam. , 1995, Physical review. B, Condensed matter.

[8]  Mark A. Miller,et al.  Archetypal energy landscapes , 1998, Nature.

[9]  M. R. Lemes,et al.  Application of artificial intelligence to search ground-state geometry of clusters , 2002 .

[10]  Sigurd Schelstraete,et al.  Finding Minimum-Energy Configurations of Lennard-Jones Clusters Using an Effective Potential , 1997 .

[11]  J. Doye,et al.  Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms , 1997, cond-mat/9803344.

[12]  M. R. Lemes,et al.  Generalized simulated annealing: Application to silicon clusters , 1997 .

[13]  J. Straub,et al.  Approximate solution of the classical Liouville equation using Gaussian phase packet dynamics: Application to enhanced equilibrium averaging and global optimization , 1993 .

[14]  Caizhuang Wang,et al.  Structures and dynamical properties of C{sub n}, Si{sub n}, Ge{sub n}, and Sn{sub n} clusters with n up to 13 , 2000 .

[15]  Feng Ding,et al.  Structural transition of Si clusters and their thermodynamics , 2001 .

[16]  Masao Iwamatsu,et al.  Global geometry optimization of silicon clusters using the space-fixed genetic algorithm , 2000 .

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

[18]  A. Shvartsburg,et al.  STRUCTURES OF GERMANIUM CLUSTERS : WHERE THE GROWTH PATTERNS OF SILICON AND GERMANIUM CLUSTERS DIVERGE , 1999 .

[19]  Koblar A. Jackson,et al.  Density-functional-based predictions of Raman and IR spectra for small Si clusters , 1997 .

[20]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[21]  L. Mitas,et al.  Quantum Monte Carlo determination of electronic and structural properties of Sin clusters (n <= 20). , 1995, Physical review letters.

[22]  J. Northby.  Structure and binding of Lennard‐Jones clusters: 13≤N≤147 , 1987 .

[23]  M. V. Ramakrishna,et al.  Combined tight‐binding and density functional molecular dynamics investigation of Si12 cluster structure , 1996 .

[24]  Bicai Pan,et al.  Structures of medium-sized silicon clusters , 1998, Nature.

[25]  M. R. Lemes,et al.  Combining genetic algorithm and simulated annealing: A molecular geometry optimization study , 1998 .

[26]  Koblar A. Jackson,et al.  CALCULATED POLARIZABILITIES OF INTERMEDIATE-SIZE SI CLUSTERS , 1999 .

[27]  A. Sieck,et al.  Structure and vibrational spectra of low-energy silicon clusters , 1997 .

[28]  A. Shvartsburg,et al.  Modeling ionic mobilities by scattering on electronic density isosurfaces: Application to silicon cluster anions , 2000 .

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

[30]  Harold A. Scheraga,et al.  Structure and free energy of complex thermodynamic systems , 1988 .

[31]  M. R. Lemes,et al.  Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks , 2002 .

[32]  Ho,et al.  Molecular geometry optimization with a genetic algorithm. , 1995, Physical review letters.

[33]  Martin F. Jarrold,et al.  Nanosurface Chemistry on Size-Selected Silicon Clusters , 1991, Science.

[34]  B. K. Panda,et al.  Orthogonal tight-binding molecular-dynamics simulations of silicon clusters , 2001 .

[35]  Andreoni,et al.  Equilibrium structures and finite temperature properties of silicon microclusters from ab initio molecular-dynamics calculations. , 1988, Physical review letters.

[36]  L. Mitas,et al.  Family of low-energy elongated Sin (n <= 50) clusters. , 1995, Physical review. B, Condensed matter.

[37]  A. Kityk,et al.  Infinite Lifshitz point in incommensurate type-I dielectrics , 1999 .

[38]  H. Scheraga,et al.  Global optimization of clusters, crystals, and biomolecules. , 1999, Science.