BrainChip and Unigen jointly launch an edge AI server for complex applications

By Abigail Opiah │Edge Industry Review

BrainChip Holdings has announced a partnership to deliver a new configuration of the recently released Unigen Cupcake edge AI server, a solution based on BrainChip’s Akida neuromorphic processor.

The company notes that the Cupcake edge AI server is a small form factor solution that can run complex AI applications at the edge. These applications can also run close to the source of data, without relying on the cloud or internet connections.

In leveraging Akida’s data-processing capabilities, the device offers unparalleled efficiency, precision, and economy of energy in a wide array of use cases such as industrial, automotive, healthcare, robotics, IoT and security-based applications, according to BrainChip.

Modeled after the human brain, the Akida neuromorphic processor processes information in a way that mimics the brain’s neural networks. This unique architecture enables the processor to excel at tasks such as pattern recognition, making it exceptionally well-suited for applications in edge AI.

“We are proud to collaborate with BrainChip to bring a new vision to the world of edge AI solutions,” says Paul Heng, president, and CEO of Unigen.

“The Cupcake edge AI server can unleash the full potential of AI technology. We look forward to expanding our AI partnership network with BrainChip to deliver a unique Cupcake configuration to customers who are looking for a smart, sustainable, and secure edge AI solution.”

Unigen says it will provide end-to-end solutions for the Cupcake edge AI server, from engineering to mass production.

Unigen’s manufacturing facilities in the U.S.A. and Vietnam, along with its proprietary business intelligence tools, aim to ensure high-quality products and services for customers across a variety of industries.

Elsewhere, BrainChip unveiled a preview of its edge box powered by neuromorphic technology. Developed in partnership with VVDN Technologies, this device showcases low power and a digital, event-based, neuromorphic AI IP, BrainChip notes.

 

Scroll to Top