Practical Ariticial Intelligence Enabler


Neuromorphic AI semiconductor


Contact Us

The NM500 is a neuromorphic chip opening new frontiers for smart sensors, IOT, machine learning, and cognitive computing. Its neurons can learn and recognize patterns extracted from any data sources, such as images, audio waveform, bio signals, text and more, with less energy and complexity than modern microprocessors. NM500 neurons are especially suitable to cope with ill-defined, fuzzy data, high variability of context, and even novelty detection. Last but not least, the NM500 is a Wafer Level Package (64 WLP), which can be easily assembled into a network of thousands to millions of neurons, or integrated into an application-specific multi-chip module or 3D stack.

The NM500 is manufactured under a license of the NeuroMem® technology from General Vision Inc.

Automatic Object Classification with NM500

Watch More Demo Video?



ANN Attributes

Neuron capacity 576 neurons
Neuron memory size 256 bytes
Recognition status Identified, Uncertain or Unknown
Logic Classifiers Radial Basis Function(RBF) | K-nearest Neighbor (KNN)
Distance Norms L1(Manhattan), Lsup

Electrical and IOs

Clock frequency 35 MHz for single chip, 18 MHz for chain of multiple chips
I/O Parallel bus (26 lines)
Electrical 3.3 V I/O operation, 1.2V core
Power Consumption < 150 mW in active mode (CS_low)at 1.2V and 3,3V
Package 64-pin WLP 4.6×4.5×0.77(mm)


NM500 Hardware Manual.PDF
Neuromem Technology overview.pdf
Neuromem Technology Reference Guide.pdf
NeuroMem API.pdf
View More

Related Videos

Automatic Object Classification

Smart RC Car

Smart LED

View More