École Nationale Supérieure de
Techniques Avancées

Abstract

In recent years, Deep Learning (DL) has enabled many new advances in a large number of fields (robotics, image processing, finance, translation and many others). Deep Learning is a part of machine learning that structures algorithms in layers to create a neural network that, when trained, can make decisions on its own. Art is one of the fields that is starting to undergo a revolution due to the appearance of artificial intelligence. New software using this new technology makes it possible to generate and classify works of art. This report presents the state of the art in artistic classification deep learning models capable of integrating more than one attribute. These models are able to include feature recognition and can incorporate expert knowledge.