Addressing advanced cloud and edge applications, BrainChip's Akida Pico is claimed as the lowest power acceleration co-processor for compact and ultra-low-power portable and intelligent devices. The Akida Pico accelerates case-specific neural-network models with an energy-efficient digital architecture, offering secure personalization for applications such as voice wake detection, keyword spotting, speech noise reduction, presence detection, appliance voice interfaces, and more.
Based on the Akida2 event-based computing platform configuration engine, the Akida Pico is well-suited for waking up microcontrollers or larger system processors. Featuring battery-powered operation of less than a milliwatt, it has a neural network to filter out false alerts to preserve power consumption.
BrainChip’s MetaTF software flow enables developers to compile and optimize their specific temporal-enabled neural networks on the Akida Pico without having to learn a new machine-language framework. At the same time, it rapidly develops and deploys AI applications for the edge.
"Like all of our edge AI enablement platforms, Akida Pico was developed to further push the limits of AI on-chip compute with low latency and low power required of neural applications,” said Sean Hehir, CEO at BrainChip. “Whether you have limited AI expertise or are an expert at developing AI models and applications, Akida Pico and the Akida Development Platform provides users with the ability to create, train, and test the most power- and memory-efficient temporal-event-based neural networks quicker and more reliably.”
An event-based compute platform useful for early-detection, low-latency solutions for robotics, drones, automotive, and traditional sense-detect-classify-track solutions, BrainChip’s Akida also has access to a range of software, hardware, and IP products that can be integrated into existing and future designs, with a roadmap for customers to deploy multimodal AI models at the edge.
