About the Artwork
In artificial intelligence ‘Latent Space’ refers to a mathematical space which maps what a neural network has learnt from training images. Once it has been trained it understands all images of trees as existing in a specific area, and all images of birds in another.
The neural network can be reverse engineered to create fake images from these coordinates*. But what if it was given a new path to travel between these recognisable points, instead moving through the in-between space?
Latent Space is a video snap-shot of an A.I. algorithm in its infancy trained using 14.2 million photographs** continuously producing new images.
For this iteration, a new soundscape by The Analog Girl was commissioned in partnership with MSCTY x Sculpture in the City.
Special thanks to Anh Nguyen et al. at Evolving-AI for their research.
* Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space (2016)
** ImageNet: A Large-Scale Hierarchical Image Database (2009)
Year: 2017 (2021 iteration)
Jake Elwes’ Latent Space will be screened the months of June (15 June onwards), July, September, November 2021, January, March and May 2022.
Copyright the artist. Photo: © Nick Turpin
Material
Digital Video made using artificial intelligence, 6 hour loop