neural networks

Deep Learning from Vasulkas’ Video Archive

Jana Horáková (CZ), Jiří Schimmel (CZ) et al.

The goal of the project is to experimentally test the utility of artificial neural networks in service of media art historiography and theory. Artificial neural networks conduct iconographic and audiographic analyses of the Woody and Steina Vasulka video archive.

ULTRACHUNK (unfortunately canceled)

Jennifer Walshe (IE), Memo Akten (TR)

What are the implications of using your voice to improvise with a neural network? Composer Jennifer Walshe and artist Memo Akten present ULTRACHUNK (2018), a neural network trained on a corpus of Walshe’s solo vocal improvisations. Here, Walshe wrangles with an artificially intelligent duet partner – one that reflects a distorted version of her own improvisatory language and individual voice.