Contemporary AI systems still lack high-level cognitive and learning skills. With the help of digital neuromorphic chips, scientists now aim to accurately model how humans can quickly and easily learn a cognitive task, such as a new board game.
Inspired by the brain’s structure, IBM and Cornell University researchers have developed an efficient, scalable, and flexible non–von Neumann architecture in a 5.4-billion-transistor chip with 4096 neurosynaptic cores interconnected via an intrachip network that integrates 1 million programmable spiking neurons and 256 million configurable synapses.
Qualcomm delivers new computer processors – Qualcomm Zeroth – that mimics the human brain and nervous system so devices can have embedded cognition driven by brain inspired computing.