Generating the conformational properties of a polymer by the restricted Boltzmann machine

In polymer theory, computer-generated polymer configurations, by either Monte Carlo simulations or molecular dynamics simulations, help us to establish the fundamental understanding of the conformational properties of polymers. Here, we introduce a different method, exploiting the properties of a machine-learning algorithm, the restricted Boltzmann machine network, to generate independent polymer configurations for self-avoiding walks (SAWs), for studying the conformational properties of polymers. We show that with adequate training data and network size, this method can capture the underlying polymer physics simply from learning the statistics in the training data without explicit information on the physical model itself. We critically examine how the trained Boltzmann machine can generate independent configurations that are not in the original training data set of SAWs.