Fall of the House of Usher II (2017)

Drawings made from the GAN generated animation


Creating my own datasets is core to my work. Working on The Fall of the House of Usher, I laboriously created by hand datasets based on the original film and then by processing and reproducing these by using specially modified algorithms, I have created a system of loops and feedbacks that use and enhance machine learning as an integral part of the work’s material and process. I then used what was generated by the GAN to form the basis of the next training set. Style in drawing always evolves but because I drew in this style for so long, it has changed how I now draw and paint a picture. The concepts of repeating, remembering and recreating that came out of the process of making Fall of the House Usher, as well as the shadow of all of this, decay, is central to the work.