Edge Impulse, a platform enabling ML at the edge and BrainChip a neuromorphic AI IP technology provider recently announced support for the deployment of Edge Impulse projects on the BrainChip MetaTF platform. The platform helps developers to design and build enterprise-grade machine learning applications which can be trained on real sensor data, in a low or no code environment. The ML algorithms can be quantised, converted and optimised to Spiking Neural Networks (SNN), that is compatible with, and can be deployed on BrainChip Akisa Devices.
“We’re delighted to support BrainChip’s proliferation of their Akida technology,” said Jan Jongboom, CTO at Edge Impulse. “The combination of BrainChip’s advanced technology and Edge Impulse’s industry-leading developer experience gives users an easy and seamless way for deploying ML at the edge using efficient and essential SNNs algorithms that helps the advancement of solving real-world problems of all types.”
“Being the commercial leader in edge AI on-chip learning and neuromorphic AI IP availability, it is critical for BrainChip to establish our ecosystem with key partnerships and technology leaders such as Edge Impulse,” says Anil Mankar, Chief Development Officer at BrainChip. “Working together, both companies are creating an advantage for the ML community. This is only the beginning of how we see our Akida technology expanding into the ecosystem.”
ML/AI developers can create Akida-compatible applications using the Edge Impulse expert mode in the learning block and utilise the BrainChip MetaTF model deployment block to use Tensorflow models to quantise them to complete or mixed low-precision bits, from 1 to 4 bits. This also allows the implementation of quantisation-aware training to retain the performance. The model can also be converted into an Akida-based SNN and developers can download them to be deployed on BrainChip Akida development kits.
Edge Impulse has integrated BrainChip’s MetaTF SDE so that newbies to ML/AI and Akida can easily adapt to the benefits of the technology.