In this article, we propose that new architectural design practices might be based on machine learning approaches to better leverage data-rich environments and workflows. Through reference to recent architectural research, we describe how the application of machine learning can occur throughout the design and fabrication process, to develop varied relations between design, performance and learning. The impact of machine learning on architectural practices with performance-based design and fabrication is assessed in two cases by the authors. We then summarise what we perceive as current limits to a more widespread application and conclude by providing an outlook and direction for future research for machine learning in architectural design practice.

No abstract

No abstract

No abstract

This chapter describes a research thread at CITA which explores how computation and a challenging of traditional material practice can impact the use of timber in architectural design and fabrication. Several past research projects at CITA have demonstrated the potential for streamlining the design-to-production process using computational tools, and the value of working in concert with the inherent properties of wood. Current research continues this thread through a participation in the Innochain research network (http://innochain.net/) and collaboration with industrial partners White Arkitekter AB and Blumer-Lehmann AG. Through the embedding of digital tools within established timber design a fabrication processes, new workflows are proposed which could lead to more intelligent design decisions, optimized building components, and new timber morphologies. Keywords Wood design • Complex timber structures Parametric design and fabrication strategies • Optimization of wood architectures Digital wood workflows