AI Driven Creativity in Early Design Education: A pedagogical approach in the age of Industry 5.0

Kavakoglu A. A., Almag B., Eser B., Alagam S.

40th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2022, Ghent, Belgium, 13 - 16 September 2022, vol.1, pp.133-142 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 1
  • City: Ghent
  • Country: Belgium
  • Page Numbers: pp.133-142
  • Keywords: Artificial Intelligence, Computational Creativity, Design Education, StyleGAN2-ADA
  • Istanbul Technical University Affiliated: Yes


© 2022, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.This study presents a pedagogical experiment on the integration of AI into the project studio in the early stages of design education. The motivation of the study is to support creative encounters in design studios by promoting student-design representation, student-student, and student-artificial intelligence (AI) interaction. In the scope of this study, a short-term studio project is used as a case study to examine these creative encounters. The experiment covers five stages that enable a recursive analysis-synthesis action. The stages include (i) precedent analysis of a given set of building fagades images, (ii) feature extraction, (iii) composing new fagade representations through employing previously generated features, (iv) training an AI by the use of styleGAN2-ADA with the outcomes of stage 3, (v) Use of synthetically generated fagade images as a design driver. The pedagogical experiment is evaluated through the lenses of novelty, style, surprisingness, and complexity concepts. The challenges and potentials are introduced, as well as elaborations on the future directions of the interplay between AI-oriented making and first-year student making.