Edge Impulse, a platform that enables machine learning at the edge, and neuromorphic AI provider BrainChip have teamed up to allow Edge Impulse projects on the BrainChip MetaTF platform.
Through their cooperation, developers can now use the BrainChip Akida platform to create and train machine learning models that are optimised for and compatible with the spiking neural network (SNN).
For new and existing projects, engineers must use the BrainChip MetaTF model deployment block integrated on the platform to activate this feature. The feature will be free for users and enterprise developers to develop and validate neuromorphic models for deploying robust edge use cases.
Jan Jongboom, CTO at Edge Impulse, said: “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 help the advancement of solving real-world problems of all types.”
A reference project targeting image classification is currently available as an Edge Impulse public project, giving experts a head-start with developing algorithms for the next generation of neuromorphic computing.
The project allows ML experts to create Akida-compatible models using the Edge Impulse expert mode. It also allows for the use of Tensorflow based models that can be quantised as complete or mixed low-precision bits, from 1 to 4 bits.
Anil Mankar, chief development officer at BrainChip, added: “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. Working together, both companies are creating an advantage for the ML community.”
Want to learn more about edge computing from industry leaders? Check out Edge Computing Expo taking place in Amsterdam, California and London.
Explore other upcoming enterprise technology events and webinars powered by TechForge here.
