IoT AI specialist SensiML has launched an open-source AutoML solution for edge AI/ML applications. The company claims this as the first AutoML solution for IoT edge servers, and brings that market to parity with current enterprise AI models.

AutoML, or automated machine learning, simplifies and speeds up the process of creating machine learning models. It makes machine learning more accessible to developers who may not have specialised data science knowledge. Building ML models for IoT microcontrollers and edge SoCs can be particularly complex because it requires blending data science with embedded code optimisation for devices with limited memory and compute power. Automated machine learning helps developers overcome such challenges.

The new AutoML solution is part of SensiML’s Analytics Studio. This is used across a range of IoT edge devices including: wearable devices and garments that analyse and coach proper human motion and ergonomics in real-time; predictive maintenance and anomaly detection sensors that recognise and react locally to faults in factory/plant machinery, pumps, and valves; and building automation and security endpoints with acoustic event detection, keyword recognition, and speaker identification.

SensiML’s Analytics Studio provides IoT Edge AI software development with: platform agnostic model generation; time-series sensor inputs; rapid innovation; and flexibility.

“Four years ago, QuickLogic, our parent company, launched the first open-source eFPGA solution,” said Chris Rogers, CEO of SensiML.  “We are leveraging this success to democratise edge AI/ML development with our robust tools. This open-source initiative will accelerate edge AI/ML adoption, benefit end-user flexibility, and boost SensiML’s SaaS growth and private-label tooling value for our growing list of industry partners.”