Neuromorphic computing systems for software-defined radio devices

1 min read

BrainChip, a specialist in neuromorphic artificial intelligence (AI) IP, and Lorser Industries, a provider of system-level manufacturing and integration, are to use BrainChip’s Akida technology to deliver neuromorphic computing solutions for software- defined radio (SDR) devices.

The partnership will look to leverage Lorser’s expertise in SDR design and manufacturing and BrainChip’s neuromorphic technology to deliver intelligent solutions that will enhance the adaptability, reliability, and scale of SDR devices.

In addition to sending and receiving shortwave and broadcast radio worldwide, SDR is an asset in astronomy, aerospace, geography, oceanography, navigation, and logistics. Akida’s neural network processing allows SDR devices to perform advanced tasks such as signal detection, classification, modulation/demodulation, encryption/decryption, and detect anomalies in signal or acoustic data with AI and machine learning (ML).

“We believe that neuromorphic computing is the future of AI/ML, and an SDR with neuromorphic AI/ML capability will offer users significantly more functionality, flexibility, and efficiency,” said Diane Serban, CEO of Lorser Industries. “The Akida processor and IP is the ideal solution for SDR devices because of its low power consumption, high performance, and, importantly, its ability to learn on-chip, after deployment in the field.”

“BrainChip and Lorser share a common interest in creating intelligent devices that can manage communication in a variety of different and evolving environments,” said Rob Telson, Vice President of Ecosystems & Partnerships at BrainChip. “Lorser, with their leadership in advanced SDR technology is the ideal partner for us to work with on a breakthrough device with the ability to utilize AI/ML to identify patterns, detect anomalies and intelligently adapt to a range of scenarios.”

Akida powers next-generation edge AI in a range of industrial, home, automotive, and scientific environments. The fully digital, customisable, event-based AI neural processor and IP has been developed for advanced AI/ML such as intelligent sensors, medical devices with extended battery life, high-end video-object detection, and ADAS/autonomous systems.

Akida’s neuromorphic architecture can learn real-time on-chip, and limits energy consumption to micro watt to milli-watt ranges, making it suitable for low-power, high-efficiency applications.

BrainChip is actively developing the Essential AI Ecosystem of collaborative partners: best-in-class semiconductor, software, and commercialization leaders, jointly demonstrating interoperability, functionality, and vertical value.