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 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|