Success! Thanks for contacting us.

Encoding Motion

We have created a suite of publicly-accessible tools for generating novel sequences of choreography as well as tunable variations on input choreographic sequences using recurrent neural network and autoencoder architectures. These methods have been developed using improvisational dance from our team members, recorded using a state-of-the-art motion capture system with a rich density of over 50 datapoints representing the human form.

Photo Credit: Jessica Todd Harper

Our Mission

We develop machine learning-based tools to inform movement-based research. We believe that technology, in conjunction with physical practice, can enhance embodied learning. We are equally interested in ethical, aesthetic, and technical questions. We aim to make kinesthetic experimentation accessible to all.

Photo Credit: Stephanie Anestis

Our Team

Mariel Pettee
Department of Physics
Yale University
Chase Shimmin
Department of Physics
Yale University
Doug Duhaime
Digital Humanities Lab
Yale University
Ilya Vidrin
Harvard Dance Center
Harvard University
Raymond Pinto
Broadway Dancer
Juilliard Alumnus

Get in touch