R

RADAR CONTEMPORARY

  • Facebook
  • Instagram
Still from exhibited work

© Andreas Refsgaard

Andreas Refsgaard

Aagaards glasplader hacked, 2019

While the digital impacts our mnemonic capacities, historical archives are also digitized affecting how we collectively remember the past. Together with a StyleGAN model, Andreas Refsgaard re-writes our history in the video work Aagaards Glasplader. A generative adversarial network (GAN) is a machine-learning system that can produce an image from a preexisting visual database. From this database, it intercepts patterns and information, after which it can demonstrate its own reverie of the world. Refsgaard has run portrait photos from the mid-19th century through the model, generating new portraits of a non-existing past accompanied by likewise generated historical biographies. It is just plain math, and yet this maneuver can be described as a symbiotic creative process between machine and human. Refsgaard’s work imitates how machine-vision, such as intelligent surveillance cameras and image recognition on social media, detects and analyzes objects, faces, and actions in our everyday surroundings. 

                                                      Ida Schyum

cand.mag in art history

                                                             

 

Andreas says

Aagaards Glasplader is a collection of high-resolution portrait photos from 1857-1880.

I trained a StyleGAN model to generate new portraits of non-existing people. I used short historical biographies of the people from the collection to have a GPT-2 model produce new texts about the generated people, letting it dream about how their lives might have been.

 

© 2020, Radar Contemporary