Innatera Unveils Pulsar Neuromorphic Processor at Computex 2025

Innatera, a Netherlands-based developer of neuromorphic computing solutions, announced the launch of Pulsar, its first commercially available microcontroller to bring brain-like intelligence into edge devices. Born from more than a decade of pioneering research, Pulsar delivers up to 100X lower latency and 500X lower energy consumption than conventional AI processors. With this breakthrough, Innatera brings a new class of ultra-efficient, brain-inspired intelligence directly to the sensor edge.
  With sensors embedded in everything from wearables and smart homes to cars and industrial systems, the need for real-time, secure, energy-efficient data processing at the edge has never been greater. Pulsar tackles this challenge head-on by processing data locally and intelligently, at the sensor level – eliminating the need to rely on brute-force compute in power-hungry edge processors or data centers to make sense of sensor data.

"Pulsar is not just another AI chip – it represents a fundamental shift in how we bring intelligence to the edge," says Sumeet Kumar, co-founder and CEO of Innatera. “This launch is the culmination of over a decade of deep research and engineering in neuromorphic computing, combined with a groundbreaking heterogeneous architecture. It marks the moment that our brain-inspired technology becomes ready for mass-market deployment. As demand for real-time, power-efficient intelligence in edge devices continues to grow, Pulsar delivers the capabilities that traditional AI hardware simply can’t – ultra-low latency, minimal power draw, and on-device decision-making. More importantly, it lays the foundation for a new class of intelligent systems that are adaptive, autonomous, and scalable. Pulsar is our first major step toward making that future a reality."
  Pulsar introduces a compute architecture based on Spiking Neural Networks (SNNs), a generational leap in AI hardware that processes data the way the brain does, focusing only on changes in input. This event-driven model dramatically reduces energy use and latency while delivering precise, real-time decision-making. Pulsar goes even further by combining neuromorphic compute with traditional signal processing in a revolutionary architecture. Integrating a high-performance RISC-V CPU and dedicated accelerators for Convolutional Neural Networks (CNNs) and Fast Fourier Transform (FFT), this architecture provides exceptional versatility on a single chip.

Pulsar gives product teams a shortcut to smarter features that were previously off-limits due to size, power, or complexity. Filtering and interpreting sensor data locally keeps the main application processor asleep until truly needed, in some cases, eliminating the need for a main application processor or cloud computing, extending battery life by orders of magnitude. With sub-milliwatt power consumption, Pulsar makes always-on intelligence truly viable, enabling everything from sub-millisecond gesture recognition in wearables to energy-efficient object detection in smart home systems. For example, it achieves real-time responsiveness with power budgets as low as 600µW for radar-based presence detection and 400µW for audio scene classification.
  "The combination of Innatera’s Spiking Neural Processor (SNP) and Socionext’s highly integrated, sophisticated radar sensor technology introduces a powerful new approach to reducing power consumption and minimizing false detections in challenging applications, such as battery-powered devices," says Matthias Neumann, Senior Marketing Manager Smart Sensor & Smart Devices at Socionext. “We are confident that this collaboration will accelerate the adoption of radar sensing solutions in the market, bringing cutting-edge technology to a wider range of industries.”

Pulsar transforms traditional sensors into self-contained intelligent systems. With its small memory footprint and efficient neural models, it fits into tight form factors while eliminating the need for heavy external compute and reducing reliance on complex, custom DSP pipelines. Sensor manufacturers can now deliver plug-and-play smart sensor modules, accelerating development and time to market.

"Aria Sensing is committed to providing advanced, highly intuitive Ultra-Wideband system-on-chip and complete solutions. The Pulsar microcontroller by Innatera facilitates real-time sensing with exceptional energy efficiency, thereby creating opportunities for continuous operation applications," says Alessio Cacciatori, Founder and CEO of Aria Sensing. "We are particularly enthusiastic about the potential of Pulsar’s neuromorphic architecture to integrate brain-inspired intelligence into our state-of-the-art 1D/2D/3D high-resolution sensing systems, leading to enhanced speed, responsiveness, and significantly improved power efficiency."
  Innatera’s Talamo SDK makes neuromorphic development approachable. Developers can build spiking models from scratch, in a PyTorch-based environment, simulate, optimize, and deploy with ease.

To further support this ecosystem, Innatera is launching its developer program, now open to early adopters. More than just a portal, it’s the foundation of a growing community designed to accelerate innovation, share knowledge, and empower members to build the next generation of intelligent edge applications together. An upcoming open-source PyTorch frontend and marketplace will create an even more collaborative ecosystem for neuromorphic AI.

"As a trusted solution partner for innovative semiconductor technologies, SmartSoC is proud to collaborate with Innatera to bring cutting-edge AI solutions like Pulsar to market. Pulsar’s unique neuromorphic architecture perfectly complements our mission to deliver smarter, more efficient products to customers across Europe and India, enabling a new generation of intelligent edge applications," says Bharath Desareddy, CEO, SmartSoC Solutions.
www.innatera.com