Deep learning is rapidly becoming a standard tool in many scientific disciplines including astronomy. I will review recent and on-going work on several applications of deep learning techniques to galaxy evolution related problems. I will show first examples of how deep learning can help reducing systematics in photometric and structural measurements of galaxies in the framework of future big-data missions such as Euclid. I will then discuss how machine learning can be used to improve the link between the theory of galaxy formation and observations. Examples of how different network configurations can be efficiently used to classify galaxies into different evolutionary stages even when no apparent features are visible will be shown. I will also briefly discuss unsupervised approaches based on generative models to compare numerical simulations and observations and detect anomalous objects. In my talk I will also try to show possible solutions to known limitations such as uncertainty estimation, small training sets and the “black box" problem.