The release extends the tool’s capability to enable on-device learning of AI models for anomaly detection inside intelligent sensors.
Designers will be able to use the NanoEdge AI Studio to distribute inference workloads across multiple devices including microcontrollers (MCUs) and sensors with ISPUs in their systems, significantly reducing application power consumption. Always-on sensors that contain the ISPU can perform event detection at very low power, only waking the MCU when the sensor detects anomalies.
The tool provides a complete end-to-end automated workflow that eases development of high-performing AI algorithms such as anomaly detection, classification, and regression. Increasing convenience and efficiency, on-device learning also permits development without requiring an exhaustive dataset to manage pre-deployment training. In addition, support for incremental learning adds extra flexibility to complete partially trained models.
The libraries generated by NanoEdge AI Studio can run on any STM32 MCU, from entry-level devices containing the Arm Cortex-M0 core to the high-performance MCUs containing the Cortex-M7 core. Newly-added support for ISPU-enhanced sensors includes the recently announced ISM330ISN 6-axis inertial measurement unit (IMU).
Scheduled for release at the end of June, the latest version of NanoEdge AI Studio delivers support for embedded AI development that combines dedicated hardware, software, tools, sample code, support and training for developers.
NanoEdge AI Studio enabling the creation of libraries designed for specific ISPU part numbers is available from the company's website.
