In edge IoT systems, reduced workload on microcontroller chip brings down the total power consumption. STMicroelectronics is offering its machine learning design software called NanoEdge AI Studio to design AI leveraging edge systems, where it recently updated this software to support smart sensors embedding intelligent sensor processing unit. The new version of software has the capacity to handle on-device learning of AI models for anomaly detection inside intelligent sensors.
NanoEdge AI Studio reduces the power consumption by distributing inference workloads across multiple devices including microcontrollers (MCUs) and sensors with ISPUs in their systems. The artificial intelligence algorithms ensures low power consumption and triggers microcontroller into operation mode from sleep mode only when the sensor detects anomalies.
ST says this tool provides a complete end-to-end automated workflow that significantly 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.
NanoEdge AI Studio generated libraries can run on any STM32 microcontrollers starting from Arm Cortex-M0 core powered microcontrollers to the high-performance microcontrollers having Cortex-M7 core. Newly-added support for ISPU-enhanced sensors includes the recently announced ISM330ISN 6-axis inertial measurement unit (IMU), says ST.
The updated version of this software is expected to be available June 2022.
NanoEdge AI Studio enabling the creation of libraries designed for specific ISPU part numbers is available at no charge on ST.com.
To learn more about this visit https://www.st.com/nanoedgeaistudio