Latent Space :::
Machine Learning 2020
Latent Space is a journey through the landscape of lockdown, hallucinated by a deep neural network. The project trained an artificial intelligence, a deep neural network, on all the landscape photographs I took during six months of lockdown.
While AI, or more specifically GANs (Generative Adversarial Networks), are noted for their ability to generate photo-realistic images, these photographs documenting my walks within the limited range of lockdown regulations, were too few in number and diverse in content to achieve perfect renditions of landscapes that never existed.
Instead, the trained AI works within the gaps and omissions to produce evocative, abstract and painterly approximations; landscapes that emerge from deep within the latent space of the neural network. This is the deep dream of the lockdown landscape: a series of videos and images generated by the neural network, where a process of machinic abstraction hallucinates the constrained and incomplete experience of lockdown.
Visit Latent Space's dedicated site