A Chinese scientific team has developed a new 'brain-like' chip that operates on reduced energy consumption, the team introduced Speck, a low-power neuromorphic chip capable of dynamic computing.
The human brain is an incredibly complex neural network, it can dynamically allocate attention based on stimulus, a process known as the attention mechanism, consuming only 20 watts, significantly lower than that of current AI systems. Therefore, neuromorphic or brain-like computing offers promising energy-saving machine intelligence.
Speck combines a dynamic visual sensor and a neuromorphic chip on one chip, developed through a collaborative algorithm-software-hardware design, can achieve energy-efficient spike-based computing, offering significant advantages over traditional AI systems. It can handle visual tasks with just 0.7 milliwatts, providing an energy-efficient, responsive, and low-power solution for AI applications.
This work offers artificial intelligence applications a brain-inspired intelligent solution characterized by exceptional energy efficiency, minimal latency and reduced power consumption, said Li Guoqi, one of the corresponding authors of the study. This innovative development marks a significant advancement in brain-computer interface research, offering new insights into the realm of artificial intelligence and cognitive computing.