INNK: A Deep Learning Game

PROJECT OVERVIEW

This project is a collaboration between Drs. Jichen Zhu (Digital Media, Drexel) and Sebastian Risi (Digital Design, IT University of Copenhagen).

iNNK, a multiplayer drawing game where human players team up against a neural network (NN).

The players need to successfully communicate a secret code word to each other through drawings, without being deciphered by the NN.

With this game, we aim to foster a playful environment where players can, in a small but crucial way, go from passive consumers of NN applications to creative thinkers and critical challengers.

Twitter: @iNNkGame

Play iNNk online (not working)

SPONSOR

None

TEAM MEMBERS

Active Members

past members

PUBLICATIONS

“Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning”.

M. Löwe, J. Villareale, E. Freed, A. Sladek, J. Zhu, and S. Risi.

In Proceedings of the Foundation of Digital Games Conference (FDG’21), 2021. Best Paper Award.

“iNNk: A Multi-Player Game to Deceive a Neural Network”.

J. Villareale, A. Acosta-Ruiz, S. Arcaro, T. Fox, E. Freed, R. Gray, M. Löwe, P. Nuchprayoon, A. Sladek, R. Weigelt, Y. Li, S. Risi and J. Zhu. In Proceedings of the 2020 ACM Conference of CHI PLAY (CHI Play 2020), 2020.