查看文章

Neuromorphic computing, which is evolved from the imitation of biological nervous systems, has recently attracted considerable attention for its amazing capability in recognition and classification at a fraction of power. Intensive research has been conducted in this field for developing artificial synapses and neurons, attempting to mimic the behaviors of these two fundamental units in biological neural networks. Typically, the implementation of neuromorphic computing systems relies on integrating many transistors, which however, sacrifices energy efficiency and integration density. Recently, magnetic skyrmion, a swirling topological spin configuration, has been studied as a promising information carrier candidate in future ultra-dense, low-power memory and logic devices for its outstanding merits of nanoscale size, low depinning current density, high motion velocity and particle-like stability etc. To date, the research …