STMicroelectronics bolsters edge AI tools with new developer cloud

Semiconductor

Fin is a former junior editor at TechForge.


Dutch semiconductor firm STMicroelectronics has launched its STM32Cube.AI developer cloud to expand its edge AI portfolio.

The online development platform is designed to speed up edge application development by simplifying processes for embedded engineers and data scientists.

STMicro says it will make working with STM32 microcontrollers easier, allowing developers to bring edge AI technology to market faster.

Ricardo De Sa Earp, executive vice president general-purpose microcontroller sub-group, STMicroelectronics, said: “We are unveiling the world’s first MCU AI Developer Cloud, which works hand-in-glove with our STM32Cube.AI ecosystem. This new tool brings the possibility to remotely benchmark models on STM32 hardware through the cloud to save on workload and cost.”

The STM32Cube.AI developer cloud is a platform that lets developers build code for STM32 microcontrollers which is optimised and benchmarked by company technology.

The platform also provides an ST model zoo, including training scripts, reference models, and application examples. Pre-trained neural network models can also be deployed onto STM32 microcontroller boards to reduce validation and development time.

Embedded developers can use the platform for a variety of edge AI use cases, such as computer vision for image classification and human motion sensing for object recognition.

“Our goal is to deliver the best hardware, software, and services to meet the challenges faced by embedded developers and data scientists so that they can develop their edge AI application faster and with less hassle,” Earp added.

Combining edge AI solutions from STM32Cube.AI’s front-end with the company’s developer cloud, developers can evaluate AI model performance and decide on suitable hardware architecture.

STM32Cube.AI is used as a set of tools for engineers to develop neural network models on popular frameworks, like PyTorch, Keras, and TensorFlow Lite. Through this, pre-trained neural network models can be converted into more efficient C-code for any STM32 board.

Want to learn more about edge computing from industry leaders? Check out Edge Computing Expo taking place in Amsterdam, California and London. 

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

Author

Tags: , ,

View Comments
Leave a comment

Leave a Reply