STM32Cube.AI v7.2, Now With Support for Deeply Quantized Neural Network and Why It Matters - ELE Times

STM32Cube.AI v7.2, released recently, brings support for deeply quantized neural networks, thus enabling more accurate machine learning applications on existing microcontrollers. Launched in 2019, STM32Cube.AI converts neural networks into optimized code for STM32 MCUs. The solution relies on STM32CubeMX, which assists developers in initializing STM32 devices. STM32Cube.AI also uses X-CUBE-AI, a software package containing libraries to convert pre-trained neural networks. Developers can use our Getting Started Guide to start working with X-CUBE-AI from within STM32CubeMX and try the new feature.