Neural sensor processor
Eta Compute and Edge Impulse have announced that they’re partnering to accelerate the event and deployment of machine learning using Eta Compute’s revolutionary ECM3532, the world’s lowest-power Neural Sensor Processor, and Edge Impulse, the leading online TinyML platform. The partnership will speed the time to plug for machine learning in billions of IoT consumer and industrial products during which battery capacity has been a roadblock.
“Collaborating with Edge Impulse ensures our growing ECM3532 developer community is fully equipped to bring innovative designs in digital health, smart city, consumer, and industrial applications to plug quickly and efficiently,” said Ted Tewksbury, CEO of Eta Compute. “We believe that our partnership will help companies debut their groundbreaking solutions later in 2020.”
Eta Compute’s ECM3532 ultra-low-power Neural Sensor Processor SoC that permits machine learning at the acute edge and its ECM3532 EVB evaluation board are now supported by Edge Impulse’s end-to-end ML development and MLOps platform. Developers can register for free of charge to realize access to advanced Eta Compute machine-learning algorithms and development workflows through the sting Impulse portal.
“Machine learning at the very edge has the potential to enable the utilization of the 99% of sensor data that’s lost today due to cost, bandwidth, or power constraints,” said Zach Shelby, CEO and co-founder of Edge Impulse. “Our online SaaS platform and Eta Compute’s innovative processor are the perfect combination for development teams seeking to accurately collect data, create meaningful data sets, spin models, and generate efficient ML at a rapidly accelerated pace.”
“Trillions of devices are expected to return online by 2035 and lots of would require some level of machine learning at the sting ,” said Dennis Laudick, vice chairman of selling , Machine Learning Group, Arm. “The combination of Eta Compute’s TinyML hardware supported Arm Cortex and CMSIS-NN technology and therefore the SaaS TinyML solutions from Edge Impulse provides developers an entire solution for bringing power-efficient, edge, or endpoint ML products to plug at the fast pace required for this next era of compute.”