Interdisciplinary AI (2019)
article⁄Interdisciplinary AI (2019)
abstract⁄Architecture does not exist in a vacuum. Its cultural, conceptual, and aesthetic agendas are constantly influenced by other visual and artistic disciplines ranging from film, photography, painting and sculpture to fashion, graphic and industrial design. The formal qualities of the cultural zeitgeist are perpetually influencing contemporary architectural aesthetics. In this paper, we aim to introduce a radical yet methodical approach toward regulating the relationship between human agency and computational formmaking by using Machine Learning ML as a conceptual design tool for interdisciplinary collaboration and engagement. Through the use of a highly calibrated and customized ML systems that can classify and iterate stylistic approaches that exist outside the disciplinary boundaries of architecture, the technique allows for machine intelligence to design, coordinate, randomize, and iterate external formal and aesthetic qualities as they relate to pattern, color, proportion, hierarchy, and formal language. The human engagement in this design process is limited to the initial curation of input data in the form of image repositories of nonarchitectural disciplines that the Machine Learning system can extrapolate from, and consequently in regulating and choosing from the iterations of images the Artificial Neural Networks are capable of producing. In this process the architect becomes a curator that samples and streamlines external cultural influences while regulating their significance and weight in the final design. By questioning the notion of human agency in the design process and providing creative license to Artificial Intelligence in the conceptual design phase, we aim to develop a novel approach toward humanmachine collaboration that rejects traditional notions of disciplinary autonomy and streamlines the influence of external aesthetic disciplines on contemporary architectural production.
|
|
| Year |
2019 |
| Authors |
Ozel, Guvenc; Ennemoser, Benjamin. |
| Issue |
ACADIA 19:UBIQUITY AND AUTONOMY |
| Pages |
380-391 |
| Library link |
N/A |
| Entry filename |
interdisciplinary-ai |
