Machine learning and generative design are profoundly shaping modern life. A central critique to the value and advancement of artificial intelligence, especially in the context of architecture, is the ability for a machine to design, as well as the resulting fear that professional services may be limited. As cities continue to develop, new tools emerge to help envision and create the built environment. How can architects embrace generative design to reimagine models of sustainability, inclusive practice, and new aesthetics?
As tools in their own right, artificial intelligence and machine learning present diverse opportunities to rethink traditional workflows. Today, building data and codes are becoming more accessible. As a result, homeowners and developers can input their preferences and an optimized design is produced. One startup has gone as far to say that they can “give you the home you want without hiring an architect." Behind these ideas are generative design technologies and algorithms shaping how we live and work.
Artificial intelligence is broadly defined as the theory and development of computer systems to perform tasks that normally require human intelligence. The term is often applied to a machine or system's ability to reason, discover meaning, generalize, or learn from past experience. Today, AI already utilizes algorithms to suggest what we should see, read, and listen to, and these systems have extended to everyday tasks like suggested travel routes, autonomous flying, optimized farming, and warehousing and logistic supply chains. In short, we are already feeling the effects of AI adoption, including through architecture.
Designer and Fulbright fellow Stanislas Chaillou created a project at Harvard utilizing machine learning to explore the future of generative design, bias and architectural style. While studying AI and its potential integration into architectural practice, Chaillou built an entire generation methodology using Generative Adversarial Neural Networks (GANs). Chaillou's project investigates the future of AI through architectural style learning, and his work illustrates the impact of style on the composition of floor plans. Chaillou's work shows how an algorithm is directly related to design and how it has its own characteristics.
As AI is augmenting design, architects are working to explore the future of aesthetics and how we can improve the design process. “Algorithms can optimize performance criteria while presenting a dizzying array of visual forms and patterns,” wrote Johnson Fain principal Scott Johnson, FAIA. Increasingly, machines are designing themselves, whether through hardware, software, or peripherals. In an article last year by James Vincent in TheVerge.com, Vincent states that Google is using machine learning to help design its next generation of machine learning chips. The algorithm’s designs are “comparable or superior” to those created by humans, say Google’s engineers, but can be generated much, much faster.
By 2050, the effects of AI adoption will be widely felt across all aspects of our daily lives. As the world faces a number of urgent and complex challenges, from the climate crisis to housing, generative design provides frameworks for rethinking style, aesthetics and beauty. Now we can imagine new creative and social processes, and hopefully, work with machine learning to lay the foundation for new aesthetics.
This article is part of the ArchDaily Topics: Aesthetics, proudly presented by Vitrocsa the original minimalist windows since 1992. The aim of Vitrocsa is to merge the interior and exterior with creativity.
Vitrocsa designed the original minimalist window systems, a unique range of solutions, dedicated to the frameless window boasting the narrowest sightline barriers in the world: “Manufactured in line with the renowned Swiss Made tradition for 30 years, our systems are the product of unrivaled expertise and a constant quest for innovation, enabling us to meet the most ambitious architectural visions.”
Every month we explore a topic in-depth through articles, interviews, news, and projects. Learn more about our ArchDaily topics. As always, at ArchDaily we welcome the contributions of our readers; if you want to submit an article or project, contact us.