Performing in ML Masks

In 2016 I began experimenting with collaging together various different machine learning (ML) outputs to create performance masks. I used style transfer to mix images of my own face with the data converted styles of various artists, plastered myself over with illustrations of standardized beauty using multiple layers of landmark detection, and played with both using the masks to augment performance (of spoken poetry) and intentionally interfering with the computers ability to apply the masks. 

 

Next ML work: Recursive ML Masks 2018