Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity
arXiv:1812.05556 · doi:10.1016/j.procs.2018.11.024
Abstract
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.
arXiv comment18 pages; 6 figures. arXiv admin note: substantial text overlap with arXiv:1610.02478
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Revenge of the 'Neurds': Characterizing Creative Thought in terms of the Structure and Dynamics of Memory
- Incorporating characteristics of human creativity into an evolutionary art algorithm
- How Insight Emerges in a Distributed, Content-addressable Memory
- The Recognizability of Individual Creative Styles Within and Across Domains
- Generalizing Prototype Theory: A Formal Quantum Framework
- Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity