Creative Data Generation Using Generative Adversarial Networks

Using generative adversarial networks (GANs), we propose a framework for creative data generation that goes beyond mere reproduction of training data. Through the adversarial training of generator and discriminator, we build mechanisms that acquire novel samples and aim at a computational understanding of creative behavior in robots and artificial agents.

Related papers:

• Riku Fujimoto, Takato Horii, Tatsuya Aoki, Takayuki Nagai. “A Framework for Creative Data Generation Using Generative Adversarial Networks” (in Japanese). 33rd Annual Conference of the Japanese Society for Artificial Intelligence (JSAI), Niigata, June 2019.