Tutorial (CREPRE)

Creative Prediction with Neural Networks

Organizers: Charles P. Martin, Kyrre Glette, Jim Tørresen


The goal of this tutorial is to apply predictive machine learning models to creative data. The focus will be recurrent neural networks (RNNs), deep learning models that can generate sequential and temporal data such as text or music. When embedded in a creative interface, they can be used for “predictive interaction” where a human collaborates with, influences, and is influenced by a generative neural network. We will walk through the fundamental steps for training creative RNNs using live-coded demonstrations in Python and present live demonstrations and interactive live-hacking of our creative RNN systems.

Session 1 (11:30-12:45)
Introduction to Predictive Interaction
Generating Creative Sequences with Recurrent Neural Networks (RNNs)

Session 2 (16:15-17:30)
Interacting with RNNs
RNNs for continuous-valued data: Mixture Density Networks (MDNs)