Deep Learning in a Computational Model for Conceptual Shifts in a Co-Creative Design System
This addresses the challenge of improving human-AI collaboration in creative tasks like design, though it is incremental as it builds on existing co-creative systems with a focus on novelty metrics.
The paper tackled the problem of enhancing creativity in co-creative design by developing a computational model for conceptual shifts using deep learning and a novelty metric, and found that higher novelty in AI-generated sketches led to higher creative outcomes in a user study.
This paper presents a computational model for conceptual shifts, based on a novelty metric applied to a vector representation generated through deep learning. This model is integrated into a co-creative design system, which enables a partnership between an AI agent and a human designer interacting through a sketching canvas. The AI agent responds to the human designer's sketch with a new sketch that is a conceptual shift: intentionally varying the visual and conceptual similarity with increasingly more novelty. The paper presents the results of a user study showing that increasing novelty in the AI contribution is associated with higher creative outcomes, whereas low novelty leads to less creative outcomes.