This image is the result of 50 iterations of running these opening lines of Emily Dickinson's poem, "Because I could not stop for Death – He kindly stopped for me –", through a modified version of BigSleep, a script using OpenAI's CLIP and the generator from a BigGAN to generate images from just those first couple lines.

My work focuses on examining how trained models using natural language understanding interpret poetry -- if they can -- what poetry means in this new digital space, and for systems designed for accuracy, what does it mean for neural networks to consider poetry?