NM500, neuromorphic chip with 576 neurons

Real practical intelligence for sensor hubs with high-speed contextual recognition, novelty detection, anomaly recording without duplication, and real-time learning at the edge from streaming data.

Reconfigurable and low-power multiple recognition engines for storage devices with high-speed contextual recognition, uncertainty management, hypothesis generation for more robust decisions.

Neuron capacity 576
Neuron memory size 256 bytes
Category register 15 bits
Distance register 16 bits
Context register 7 bits
Recognition status Identified, Uncertain or Unknown
Classifiers Radial Basis Function (RBF), K-Nearest Neighbor (KNN)
Distance Norms L1 (Manhattan), Lsup