Reconfigurable AI Device Shows Brain-Like Promise
An adaptable new device can transform into all the key electric components needed for artificial-intelligence hardware, for potential use in robotics and autonomous systems, a new study finds.
The goal of \”neuromorphic\”, or brain-inspired, computer hardware is to replicate the brain’s remarkable ability to adapt to experience and process information quickly in a highly energy-efficient way. These brain features are largely due to the plasticity of its structure, which allows it to change over time. This is achieved through activities such as \”neurogenesis\” or neuron formation.
We hypothesized that if we could replicate these neurogenesis behaviors within electrical hardware, then we could create machines that could learn for the rest of their lives,\” says Shriram Ramanathan. He is an electrical engineer and materials science at Purdue University in West Lafayette, Ind.