BrainChip launches second generation Akida platform for edge AI applications
BrainChip, a provider of neuromorphic processors for edge AI on-chip processing, has revealed the latest version of its Akida platform, designed to serve the increasing demand for embedded edge AI applications. The platform uses vision transformers and spatial-temporal convolution to offer high-performance and power-efficient solutions for the network edge.
According to the company, the new Akida platform incorporates 8-bit processing for high performance. The Akida IP platform is intended for small form factor devices in healthcare and consumer electronics, such as hearable and wearable devices.
“We licensed Akida neural processors because of their unique neuromorphic approach to bring hyper-efficient acceleration for today’s mainstream AI models at the edge,” says Roger Wendelken, the senior vice president of Renesas’ IoT and Infrastructure Business Unit.
BrainChip leverages vision transformers, a specifically designed transformer, to accomplish vision processing tasks such as image recognition. BrainChip used vision transformers due to their aptitude for object detection, image classification and semantic segmentation.
Akida’s second-generation technology includes Temporal Event Based Neural Nets (TENN) spatial-temporal convolutions that allow for simplified processing of raw time-continuous streaming data including video analytics, audio classification and target tracking. The company says these abilities can enable faster design cycles and lower the cost of development.
“Our customers wanted us to enable expanded predictive intelligence, target tracking, object detection, scene segmentation, and advanced vision capabilities. This new generation of Akida allows designers and developers to do things that were not possible before in a low-power edge device,” says Sean Hehir, the CEO of BrainChip.
Article Topics
AI/ML | Brainchip | computer vision | edge AI
Comments