Edge Impulse announced official support for BrainChip's neural processor AI IP, making BrainChip the first strategic IP partner on the Edge Impulse platform. This integration will enable users to leverage the power of Edge Impulse's machine learning platform, combined with the high-performance neural processing capabilities of BrainChip's Akida™ to develop and deploy powerful edge-based solutions. Among the products supported by Edge Impulse is BrainChip's AKD1000 SoC, the first available device with Akida IP for developers.

This comes with a BrainChip Akida PCIe reference board, which can be plugged into a developer's existing system to unlock capabilities for a wide array of edge AI use cases, including Automotive, Consumer, Home, and Industrial applications. The Akida IP platform provides low-power, high-performance edge AI acceleration, designed to enable real-time machine learning inferencing on-device. Based on neuromorphic principles that mimic the brain, Akida supports today's models and workloads while future-proofing for emerging trends in efficient AI.

Now devices with the Akida IP supported by Edge Impulse can enable users to sample raw data, build models, and deploy trained embedded machine learning models directly from Edge Impulse Studio to create the next generation of low-power, high-performance ML applications. Edge Impulse and BrainChip have an established relationship, previously announcing cross-platform support, including support for deploying Edge Impulse projects on the BrainChip MetaTF platform. Some of the features in which the user community can leverage include: BrainChip's transfer learning block on Edge Impulse design studio; Quantization Aware Training (QAT); The introduction of FOMO for BrainChip's Akida; Generation of BrainChip's compatible Edge Learning Models; No-code binary generation for quick AKD1000 deployment; Performance metrics for model profiling.

The ongoing combination of BrainChip's Akida technology and Edge Impulse's platform, tools, and services will allow customers to achieve their ML objectives with fast and efficient development cycles to get to market quicker and achieve a competitive advantage.