Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity

TL;DR

This paper analyzes two deep learning algorithms for visual blending, exploring their potential as tools for computational creativity and relating their operation to human cognitive theories of creativity.

Contribution

It schematizes and explains the core mechanisms of two AI-based visual blending algorithms and discusses their relevance to human creativity theories.

Findings

Algorithms generate novel and aesthetically appealing images

They relate to human cognitive theories like conceptual blending and honing

Potential applications in computational creativity research

Abstract

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.