Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity
This work addresses the challenge of enhancing AI creativity for applications in art and psychology, though it appears incremental as it synthesizes existing methods rather than introducing a fundamentally new approach.
The authors tackled the problem of making AI-generated art more compelling and human-like by incorporating cognitive theories of human creativity into generative deep learning techniques, demonstrating how concepts like honing theory and intrinsic motivation can be computationally implemented to impact generative art.
The common view that our creativity is what makes us uniquely human suggests that incorporating research on human creativity into generative deep learning techniques might be a fruitful avenue for making their outputs more compelling and human-like. Using an original synthesis of Deep Dream-based convolutional neural networks and cognitive based computational art rendering systems, we show how honing theory, intrinsic motivation, and the notion of a 'seed incident' can be implemented computationally, and demonstrate their impact on the resulting generative art. Conversely, we discuss how explorations in deep learn-ing convolutional neural net generative systems can inform our understanding of human creativity. We conclude with ideas for further cross-fertilization between AI based computational creativity and psychology of creativity.