ARTIFICIAL NEURAL SYSTEM MODELING OF MONTE-CARLO SIMULATIONS OF POLYMERS

In this work, a neural network was used to learn features in potential energy surfaces and relate those features to conformational propertie s of a series of polymers. Specifically, we modeled Monte Carlo simula tions of 20 polymers in which we calculated the characteristic ratio a nd the temperature coefficient of the characteristic ratio for each po lymer. We first created 20 rotational potential energy surfaces using MNDO procedures and then used these energy surfaces to produce 10000 c hains, each chain 100 bonds long. From these results we calculated the mean-square end-to-end distance, the characteristic ratio and its cor responding temperature coefficient. A neural network was then used to model the results of these Monte Carlo calculations. We found that art ificial neural network simulations were highly accurate in predicting the outcome of the Monte Carlo calculations for polymers for which it was not trained. The overall average error for prediction of the chara cteristic ratio was 4,82%, and the overall average error for predictio n of the temperature coefficient was 0,89%.