Vous êtes connectés en tant qu'organisateur. Cette page est en cache jusqu'à Wed, 08 Dec 2021 11:52:07 GMT. Prévisualisez la dernière m-à-j en cliquant Rafraîchir.

RERITES: Deep Poesis Process Research

10:00 AM, vendredi 17 août 2018 (1 heure)

BDP (Big-Data Poetry)currently investigates machine learning and neural networks as tools for literary creation. The work is ongoing and open-ended. Using Tensorflow, Keras and PyTorch, neural net models are trained on a custom corpus of over 600,000 lines of contemporary poetry (from the romantic epoch to the 20th century avant garde).

Successfulmodels sequentially generate poems in an infinite loop.

Generated poems are used in two entwined creative processes: RERITES, where a human edits/distills the neural net output into books, (publishing at the rate of one book a month, April 2017 - April 2018); and as spoken word performances. The Python-based terminal then becomes a site for writing by the machine, reading by the human poet who must attempt to stitch and weave together poems from the incoherent hybrid yet often astonishing word-debris. In both processes, authorship blurs and issues arise.