Dangerous Creatures Living in The Deep

Gif animations, gallery Gallery, 2019

Dangerous Creatures Living in The Deep is a continuation of Albena Baeva’s exploration into artificial intelligence. It was presented at the router gallery Gallery as part of the wrong biennale in 2019.

What would an AI algorithm look like if it could imagine its own body? Would it choose to look like a robot as in the movies, or would it prefer to be a blond, non-threatening, girl or a cute animal? Would it choose to be female, male, animal or something else entirely; something new and unexpected?

How does an AI algorithm perceive itself? What is its self-image, and what form would it choose if it could? Albena Baeva trains a self-learning algorithm to find its identity by letting it create self-portraits. Analysing hundreds of thousands of different bodies found online, the algorithm creates new self-portraits; like avatars in its image.

The work is based on DCGAN by Soumith Chintala and art-DCGAN by Robbie Barrat algorithms. For the learning process it uses 3000 portraits of celebrities from CelebA Dataset, 4000 dogs from Standford Dogs Dataset, 5000 other animals from Oregon Wildlife, Animals-10, 10 Monkey Species, Google images, 14367 fashion models from Fashion Product Image Dataset, 14870 butterflies, moths, spiders and flowers from  Leeds Butterfly, Ecuador Moths, Costarica Moths, Flowers Recognition, Google Images.



Comments are closed.