Machine learning algorithms are the design tools of the information age

The Co-Head of Computer Design at SmithGroup explains how machine learning tools can refine data into insights, helping designers work smarter.

Technology is changing the world as we know and understand it. But have architects and designers exploited the full potential of cutting-edge digital tools? In this series of commentaries, practitioners with a visionary approach examine some of today’s most influential and disruptive technologies – such as blockchain technology, VR/AR/MR, spatial computing, machine learning and cloud computing – and consider their impact on the practice of architecture and interior design of tomorrow. The changes they describe, while predictions, will likely materialize, shaping how we plan, work, and create. Consider this a glimpse into the not so distant future.

Artwork by Ori Toor

Machine learning will enable a more integrated and informed design process by disrupting how and when architects interact with data. If we start by thinking of machine learning as a set of algorithmic tools that refine data into information much like a saw helps shape wood into furniture, the opportunities these tools present become more focused. I imagine machine learning tools will help design professionals understand the impact of decisions as they are made, not days or weeks later.

Ml Picture 4
Courtesy of SmithGroup

Methods such as surrogate modeling, which uses regressor algorithms to replace slow computational engines with an instantaneous predictive “substitute”, will support real-time, data-rich design interfaces that allow teams to react to the speed of a designer’s curiosity. I expect future engineers to function as data analysts. They will spend most of their time modeling, analyzing and explaining data rather than manually using analysis software. For example, once a design challenge is modeled parametrically and translated into structured data (an approach we call design space exploration), simple algorithms like multiple linear regression can measure which parameters have the greatest impact on performance.

Clustering algorithms, classifiers, and dimensionality reduction techniques can then be used to unravel obscure relationships that can provide actionable direction to teams. These algorithms represent only a fraction of the machine learning tools that design professionals can and should learn to use. But machine learning algorithms aren’t magic. These are tools of the information age that we can leverage to better inform the design process in the future.

Leland Curits
Leland Curtis, Co-Head of IT Design, SmithGroup Courtesy of Leland Curtis

You may also enjoy “Why Design Firms Are Turning To Cloud-Based Platforms”

Would you like to comment on this article? Send your thoughts to: [email protected]

Register here for Metropolis Think Tank Thursdays and find out what leading North American companies are thinking and working on today.