Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks

Abstract

Theoretical determination of the ground-state geometry of Si clusters is a difficult task. As the number of local minima grows exponentially with the number of atoms, to find the global minimum is a real challenge. One may start the search procedure from a random distribution of atoms but it is probably wiser to make use of any available information to restrict the search space. Here, we introduce a new approach, the Assisted Genetic Optimization (AGO) that couples an Artificial Neural Network (ANN) to a Genetic Algorithm (GA). Using available information on small Silicon clusters, we trained an ANN to predict good starting points (initial population) for the GA. AGO is applied to Si 10 and Si 20 and compared to pure GA. Our results indicate: i) AGO is, at least, 5 times faster than pure GA in our test case; ii) ANN training can be made very fast and successfully plays the role of an experienced investigator; iii) AGO can easily be adapted to other optimization problems.

Investigation of prolate and near spherical geometries of mid‐sized silicon clusters

“…Unbiased searches are important because they can be used to solve problems in general [11,12]. On the other hand, prior knowledge, if available, may be put to good use to speed up the search process [13,14]. Such an approach may be based on data mining techniques such as genetic algorithm [15][16][17] and artificial neural networks [18][19][20] or based on growth strategies [21,22,24,25].…”