CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures
id
cdrf2022_284
authors
Ralph Spencer Steenblik
year
2022
title
Developing a Hybrid Intelligence Through Hacking the Machine Learning Neural Style Transfer Process for Possible Futures
Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary
This article highlights work using machine learning in collaboration with designers for speculative world building. The process is unique because of the feedback loop, between the designer and the computational process. Worldbuilding is a speculative practice and requires vision and courage on the part of the designer. Working with machine learning neural style transfer (NST) allows the designers to consider possibilities humanity may not otherwise allow ourselves to imagine. This is important because human imagination paves the path for the future of humankind. Imagining a sustainable future requires considering unconventional solutions. Imagining non-probable futures allows humanity to glean desirable aspects to strive for. Even if a conceived future is impossible within the built environment, there are many opportunities for people to inhabit these environments virtually. Letting yourself get lost in these places is a form of travel, even when conditions limit one's ability to physically do so.