BrainChip’s technology uses a type of neuromorphic computing called spiking neural networks (SNNs) which has many attractive characteristics, including the ability to be trained instantaneously (“one-shot learning”), high accuracy and low compute overhead. This technology learns from experience, autonomously, just like a human and does not need to be trained with millions of samples like Deep Learning. It learns a pattern instantaneously and finds patterns that humans may not be aware of. SNNs can be implemented using regular logic functions, making them inherently high-performance and low-power.
