MCU enables neuromorphic processing at the edge

As Innatera’s first mass-market neuromorphic MCU, Pulsar delivers intelligence at the edge by emulating the brain’s neural networks. It uses Spiking Neural Networks that process only changes in input—enabling real-time decision making with significantly reduced energy and latency. According to Innatera, Pulsar achieves up to 100× lower latency and 500× lower energy consumption compared to conventional AI processors.

The Pulsar chip combines neuromorphic computing with conventional signal processing. In addition to its Spiking Neural Networks (SNNs), it integrates a RISC-V CPU and dedicated accelerators for Convolutional Neural Networks (CNNs) and Fast Fourier Transform (FFT). By processing data intelligently at the sensor level, Pulsar reduces reliance on power-hungry edge processors or cloud infrastructure for interpreting sensor input.

With sub-milliwatt power consumption, Pulsar enables always-on intelligence in power-constrained devices—from sub-millisecond gesture recognition in wearables to energy-efficient object detection in smart home systems. It provides real-time responsiveness with power budgets as low as 600 µW for radar-based presence detection and 400 µW for audio scene classification.

Pulsar is available now, supported by Innatera’s Talamo SDK for neuromorphic application development.

Pulsar product page

Innatera

The post MCU enables neuromorphic processing at the edge appeared first on EDN.