Description
t-SNE Map by Cyril Diagne, Nicolas Barradeau, and Simon Doury, a Google Arts & Culture experiment. Users explore an interactive 3D landscape where machine learning algorithms organized thousands of artworks by visual similarity — the more similar two artworks, the closer they appear. The project uses t-SNE (t-distributed Stochastic Neighbor Embedding), a dimensionality reduction algorithm developed by Laurens van der Maaten and Geoffrey Hinton in 2008, to project high-dimensional image features into a navigable 3D space. The result is not a geographic map but a topographic landscape of visual culture, where clusters form around shared colors, compositions, subjects, and artistic styles. Browsing the landscape reveals unexpected connections between artworks from different periods and cultures.
