Some scientific papers report that when Independent Component Analysis (ICA) is applied in the preprocessing step of designing a brain computer interface, the quality of this interface increases. At the same time, however, these papers do not provide information about the exact gain in classification precision obtained after applying different ICA algorithms. The aim of this paper is to compare three algorithms for Independent Component Analysis applied in the process of creating a brain computer interface in order to find out whether the choice of a specific ICA algorithm has an influence on the final classification precision of this interface. The comparison will be carried out with a set submitted to the second BCI Competition.