NeuroMem ICs

Non linear classifier

Identify, classify, detect  novelty, cope with non linearity, report cases of uncertainty.

Model Generator

Learning on the chip, intrinsic deduplication, tracability of the knowledge built by the neurons.

High performance

Fixed latency regardless of the number of neurons, µseconds per pattern, <150 mWatts

Available NOW

Available on ASICs, SOCs, and FPGAs and can be evaluated on a variety of platforms

CM1K

  • 1024 neurons
  • 256 bytes of memory per neuron
  • Cascadable
  • I2C (optional use)
  • Recognition stage (optional use)

NM500 chip

  • 576 neurons
  • 256 bytes of memory per neuron
  • Cascadable
  • Wafer scale package

Intel Quark SE

  • 128 neurons
  • 128 bytes of memory per neuron
  • Component of an SOC also combining an x86 MCU and a sensor subsystem