Machine learning platform Edge Impulse to support BrainChip Akida Neuromorphic IP
Edge Impulse and BrainChip have teamed up to allow Edge Impulse machine learning projects to deploy on the BrainChip MetaTF platform. The goal of their cooperation is to boost the use of edge machine learning applications for large-scale enterprise use.
Developers may now use the BrainChip Akida hardware platform to create and train machine learning models that are optimized, converted, and compatible with the spiking neural network (SNN).
For new and existing Edge Impulse 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.
“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,” said Jan Jongboom, CTO at Edge Impulse.
Recommended reading: BrainChip, Prophesee to deliver “neuromorphic” event-based vision systems for OEMs
The partnership has also provided a reference project on image classification that uses neuromorphic computing for those looking for an example project. To get started, the developers will use the BrainChip MetaTF model deployment block and leverage that to a TensorFlow-based machine learning model. The platform will also allow for the quantization of the models to low precision bits from one to four bits and help maintain the required high performance.
Once the machine learning models are ready on the Edge Impulse platform, they can be converted to Akida-based SNN and developers can directly deploy them on BrainChip Akida development kits. The platform can summarize model accuracy and efficiency and also provide configuration data.
“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.”
Article Topics
AI/ML | Brainchip | chip | edge AI | Edge Impulse | model | neuromorphic computing
Comments