In digital design practice, the connection and feedback between physical and digital modelling is receiving increasing attention and is seen as a source of creativity and design innovation. The authors present a workflow that supports real-time design collaboration between human and machine intelligence through physical model building. The proposed framework is investigated through a case study, where we test the direct connectivity of physical and digital modelling environments with the integration of artificial neural networks. By combining 3D capturing tools and machine learning algorithms, the research creates an instant feedback loop between human and machine, introducing a hybrid immediacy that puts physical model building back at the centre of the digitally focused design process. By fusing physical models and digital workflows, the research aims to create interactivity between data, material and designer already at the early stage of the design.

Digital design processes are increasingly being explored through the use of 2D generative adversarial networks (GAN), due to their capability for assembling latent spaces from existing data. These infinite spaces of synthetic data have the potential to enhance architectural design processes by mapping adjacencies across multidimensional properties, giving new impulses for design. The paper outlines a teaching method that applies 2D GANs to explore spatial characteristics with architectural students based on a training data set of 3D models of material-labelled houses. To introduce a common interface between human and neural networks, the method uses vertical slices through the models as the primary medium for communication. The approach is tested in the framework of a design course.

No abstract