Deep Neural Network Style Transfer
In fine art, especially painting, humans have mastered the skill to create unique visual experiences through complex interplay between the content and style of an image. In 2015 a research team consisting of Leon A. Gatys, Alexander S. Ecker and Matthias Bethge, managed to bring similar capabilities to machines.
The artificial system can create artistic images by using neural nets to separate the style of one image to then recombining it with the content of another. In light of the striking similarities between performance-optimised artificial neural networks and biological vision, the work done on DNN Style Transfer offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery.