|
SS22 WS22 SS23 WS23 SS24 WS24 Guidelines for Master Students
Transfer learning on organic/inorganic interfaces for different substrates Performing structure search of organic molecules on metallic surfaces requires finding the structure with the smallest energy. Using conventional density functional codes this proves to be a time consuming task since the number of possible configurations is large and individual calculations are expensive. To circumvent the computation of all possible configurations, machine learning techniques such as Gaussian process regression proved to be a useful tool to reduce the amount of calculated data. In this work we will present techniques to further reduce the data requirements by using transfer learning. Transfer learning aims to use information from a machine learning model trained on substrate A to improve the prediction of the system on another substrate B. This can then be used in order to analyze the influence of the substrate on phase diagrams and interaction energies. |