Deep Learning in a Computational Model for Conceptual Shifts in a Co-Creative Design System

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.

[1]  Pegah Karimi,et al.  Evaluating Creativity in Computational Co-Creative Systems , 2018, ICCC.

[2]  Amitava Das,et al.  Poetic Machine: Computational Creativity for Automatic Poetry Generation in Bengali , 2014, ICCC.

[3]  Brian Magerko,et al.  Drawing Apprentice: An Enactive Co-Creative Agent for Artistic Collaboration , 2015, Creativity & Cognition.

[4]  Katherine A. Brady,et al.  Modeling Expectation for Evaluating Surprise in Design Creativity , 2015 .

[5]  Björn Niehaves,et al.  Towards a Unified Design Theory for Creativity Support Systems , 2012, DESRIST.

[6]  Sungwoo Lee,et al.  I Lead, You Help but Only with Enough Details: Understanding User Experience of Co-Creation with Artificial Intelligence , 2018, CHI.

[7]  Simon Colton,et al.  The Painting Fool Sees! New Projects with the Automated Painter , 2015, ICCC.

[8]  Douglas Eck,et al.  A Neural Representation of Sketch Drawings , 2017, ICLR.

[9]  Pegah Karimi,et al.  Creative Sketching Apprentice: Supporting Conceptual Shifts in Sketch Ideation , 2018, Design Computing and Cognition '18.

[10]  Antonios Liapis,et al.  Mixed-initiative co-creativity , 2014, FDG.

[11]  Masaki Suwa,et al.  What do architects and students perceive in their design sketches? A protocol analysis , 1997 .

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[14]  John S. Gero,et al.  Design and other types of fixation , 1996 .

[15]  Pegah Karimi,et al.  Deep Learning for Identifying Potential Conceptual Shifts for Co-creative Drawing , 2018, ArXiv.

[16]  Brian Magerko,et al.  An Enactive Model of Creativity for Computational Collaboration and Co-creation , 2015, Creativity in the Digital Age.

[17]  Akshay Gupta,et al.  Viewpoints AI , 2013, AIIDE.

[18]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[19]  Ben Shneiderman,et al.  Creativity support tools: accelerating discovery and innovation , 2007, CACM.

[20]  Jason Hong,et al.  Computational Support for Sketching in Design: A Review , 2009, Found. Trends Hum. Comput. Interact..

[21]  J. Gero.  Computational Models of Innovative and Creative Design Processes , 2000 .

[22]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[23]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[24]  Vishwa Shah,et al.  Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators , 2019, CHI.