Structured Illumination Microscopy (SIM) allows us to improve the resolution of classical wide-field imaging systems by moving high-frequency components into the observable microscope region. The flexibility of SIM regarding fluorescent probes and its low illumination power requirement makes it extremely interesting for life cell imaging which is of a fundamental importance in biological research. An attractive SIM setting from the acquisition simplicity viewpoint involves the use of speckle illumination patterns. However, such a system is mainly limited by the large number of acquisitions required by the current reconstruction methods and the fact that the illumination patterns are unknown. In this project, the student will investigate the use of convolutional neural network (CNN) to the chalenging goal of both estimating the illumination patterns and reconstructing the super-resolved image from a reduced number of acquired speckle SIM images.