Neuro-Symbolic Generative Art: A Preliminary Study
This is an incremental study for artists and researchers in generative art, aiming to enhance creativity by blending neural and symbolic methods.
The authors tackled the problem of combining neural and symbolic generative art by proposing a neuro-symbolic hybrid, where a deep neural network is trained on symbolic art samples. They found that human subjects rated the artifacts and creation process as more creative than the symbolic approach 61% and 82% of the time, respectively.
There are two classes of generative art approaches: neural, where a deep model is trained to generate samples from a data distribution, and symbolic or algorithmic, where an artist designs the primary parameters and an autonomous system generates samples within these constraints. In this work, we propose a new hybrid genre: neuro-symbolic generative art. As a preliminary study, we train a generative deep neural network on samples from the symbolic approach. We demonstrate through human studies that subjects find the final artifacts and the creation process using our neuro-symbolic approach to be more creative than the symbolic approach 61% and 82% of the time respectively.