← Project List
Anna Tsuda →
4104 frames (2020) is an experimental video exploring nature, architecture and life through the lens of a machine learning algorithm trained only to understand faces. It is an attempt at revealing the inner workings of a traditionally 'black-box' machine learning model. This results in scenes of human faces deteriorating into environments as part of a delirious exploration of the farthest edges of a model’s latent space. A demonstration of a novel use case of generative adversarial networks (GANs) for video manipulation.
Video frames are fed through an inverted generative adversarial network pre-trained on a dataset of faces, outputting some latent representations of the input frames. These latent representations are then re-passed through the GAN, resulting in heavily manipulated versions of the original frames containing elements from both the original footage as well as facial features and textures reminding the viewer of the model’s intended purpose. This identity operation can be distorted by adjusting the loss function and reference images used in mapping images to the latent space, which directly affects the level of ‘obscurity’ present in the video. This results in increased creative freedom and transforms a ‘black-box’ generative model into a creative video manipulation tool.
Machine learning and artificial intelligence tools hold almost a mythical status in contemporary culture and have sparked widespread discussions on what the role of the machine is in the creative process. Considering neural networks as creative entities can be exciting, but can also lead to unattainable expectations, unwarranted fear and misplaced trust in these systems. The real dangers of the artificial intelligence of today lie elsewhere - in how the tools are inheriting their creators' unconscious biases, perpetuating inequality and enforcing existing oppressive power structures. This research and the resulting work is an attempt at gaining control over these tools and understanding their inner structures.