The chip is based on a hybrid architecture combining a many-core architecture, reconfigurable building blocks and a streamlined dataflow with hybrid coding schemes. It can not only accommodate computer-science-based machine-learning algorithms, but also easily implement brain-inspired circuits and several coding schemes. Using just one chip, the team around Luping SHI demonstrated the simultaneous processing of versatile algorithms and models in an unmanned bicycle system, realizing real-time object detection, tracking, voice control, obstacle avoidance and balance control.
Nature 572, pages106–111 (2019)
