Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity
This work provides an incremental analysis of existing AI methods for visual creativity, linking them to human cognitive theories.
The paper examines two deep learning algorithms for visual blending in convolutional neural networks, analyzing their operation and output to assess their value for computational creativity research.
We examine two recent artificial intelligence (AI) based deep learning algorithms for visual blending in convolutional neural networks (Mordvintsev et al. 2015, Gatys et al. 2015). To investigate the potential value of these algorithms as tools for computational creativity research, we explain and schematize the essential aspects of the algorithms' operation and give visual examples of their output. We discuss the relationship of the two algorithms to human cognitive science theories of creativity such as conceptual blending theory and honing theory, and characterize the algorithms with respect to generation of novelty and aesthetic quality.