Digital signal processing
The focus is on development and application of machine learning techniques for spectrally efficient optical communication systems. We employ methods from machine learning to identify and learn the impairments from the observed data and built subsequent probabilistic models. This knowledge is used to either perform impairment compensation or to quantify the amount of distortion coming from components and specific subsystems. Finally, the probabilistic model are used for synthetic impairment generation which may be very useful for performance analysis and prediction in optical networks.