1. Shadow-Less Gallery: A Gallery Design Driven by Machine Learning
23Fall, Cornell University. With Ariel Lu, Zeiad Admin, Dezhong Deng.
- Terry Pratchett
“Light thinks it travels faster than anything, but it is wrong. No matter how fast light travels, it finds the darkness has always got there first, and is waiting for it.”
This project reimagines shadow as more than a visual byproduct—it becomes the essence of spatial design. By employing a machine learning classifier system to classify shadows into ambient and sharp forms, we developed a framework that balances scientific precision with creative exploration. Shadow becomes sculpture, transforming gallery spaces into immersive environments where light, material, and time interplay dynamically. Through intersecting forms and shifting light patterns, the project invites a poetic engagement with impermanence and the ephemeral beauty of our surroundings.
At its core, this work explores the philosophical and societal potential of integrating machine learning into design. By harnessing light and shadow to shape experiences, the project proposes a future where architecture fosters reflective, harmonious relationships between people, spaces, and time, emphasizing sustainability and a profound connection to the intangible.