• Machinic Interpolations: A GAN pipeline for integrating Lateral Thinking in Computational tools of Architecture
    [BLANK]
Machinic Interpolations: A GAN pipeline for integrating Lateral Thinking in Computational tools of Architecture
Machinic Interpolations: A GAN pipeline for integrating Lateral Thinking in Computational tools of Architecture
Machinic Interpolations: A GAN pipeline for integrating Lateral Thinking in Computational tools of Architecture
Machinic Interpolations: A GAN pipeline for integrating Lateral Thinking in Computational tools of Architecture
Object Title

Machinic Interpolations: A GAN pipeline for integrating Lateral Thinking in Computational tools of Architecture

Part of

Collection: 2020 (PC020402.16) ➔ Series: Parsons School of Design MFA Design and Technology program theses


Material Category
Thesis
Description
Many of the tools used by architects to design, conceptualize and experiment have entered into the discipline from fields such as engineering, manufacturing or animation. As a result, values such as optimization, standardization and efficiency have discretely found their way into these tools and have greatly informed and constrained the possible design space. In this paper, we target the need to integrate lateral thinking strategies in digital design tools. Within this context, we propose a methodology that uses GANs and their properties as an experimentation ground to reevaluate the lateral thinking constraints in architectural tools. Specifically, we use StyleGAN and explore the ability to access its latent space as part of an architectural design process. The presented methodology constitutes a 4-step approach that draws from the abilities and properties of this space to design architecture: initializing the virtual environment of points (through training), entering the space (randomly or with an intent), moving through space (through arithmetic operations and interpolations), and finally generating a voxelized 3D form from interpolated images. By doing this, and through a demonstrated case study, we show how this series of techniques could result in unexpected spaces, resulting in creative output beyond what is produced by human capability alone.

Creator Keywords:
machine learning; experimental design; architecture tools
Date
May 3 2020
Related people
Karen El Asmar (designer)
Harpreet Sareen (thesis advisor)
Loretta Wolozin (thesis advisor)
Design
Use Restrictions
In accordance with The New School's Intellectual Property Rights Policy, copyright is held by each thesis' respective author. The responsibility to secure copyright permission rests with the user.; http://rightsstatements.org/vocab/InC/1.0/
Identifier
PC020402_2020_elask537

There’s more! What you see on this site is only what is viewable online. Please visit archives.newschool.edu to find out more about what’s in the archives.