A first physical system to learn nonlinear tasks without a traditional computer processor
Sam Dillavou, a postdoctoral fellow in the Durian Research Group in the School of Arts & Sciences, built the components of this contrasting local learning network, an analog system that is fast, energy-efficient, scalable, and can learn nonlinear tasks. Credit: Erica Moser Scientists face many trade-offs in building and scaling brain-like systems that can perform … Read more
