量子数学压缩AI模型

Tensor networks grapple with the complexities of both quantum particles and machine learning By Emily Conover | Illustrations by Hawaii A hunk of material bustles with electrons, one tick- ling another as they bop around. Quantifying how one par- ticle jostles others in that scrum is so complicated that, beginning in the 1990s, physicists developed an esoteric mathematical struc- ture called a tensor network just to describe it. A decade or so later, when quantum physicist Román Orús began studying ten- sor networks, he didn’t envision applying them to the seemingly unrelated concepts of artificial intelligence. …