Fluorescence lifetime imaging microscopy (FLIM) is a powerful technique to probe the molecular environment of fluorophores. The analysis of FLIM images is usually performed with time consuming fitting methods. For accelerating this analysis, we propose a simple neural network formed only with fully connected layers able to analyze fluorescence lifetime images. This network is called Phasor-Net and it is based on the reduction of high dimensional fluorescence intensity temporal decays into four parameters which are the phasor coordinates, the mean and amplitude-weighted lifetimes. Phasor-net is able to determine quickly and accurately the bi-exponential parameters with a lower number of photons than standard fitting methods The aim of this workshop is to introduce some deep learning algorithms used for analyzing FLIM images and to perform experimental FLIM acquisitions in living cells expressing fluorescent proteins: eGFP only for negative control and eGFP linked to mCherry for positive control. We will finally analyze these data with the Phasor-Net network implemented in a home-made software and discuss some strategies for improving the results.