Infineon advances Edge AI computing on PSOC Edge with NVIDIA TAO toolkit integration
Microcontrollers (MCU) are at the heart of modern electronics, and integrating the latest AI development and deployment workflows at the edge poses a major challenge for developers. The combination of a high-performance MCU with NPU hardware acceleration and an advanced AI fine-tuning workflows will enable developers to accelerate the deployment of AI models in low-power MCUs: Infineon has today announced support for NVIDIA TAO models on the PSOC Edge MCU family.
Infineon’s PSOC Edge MCU family features Arm Cortex-M55 processors and Ethos-U55 microNPU and enhances energy-efficient machine learning capabilities at the edge. The combination of these versatile microcontrollers with the powerful NVIDIA TAO models and fine-tuning toolkit greatly simplifies the creation, customisation, optimisation, and deployment of high accuracy vision AI models.
“NVIDIA is a key player in the AI/ML space, so we and our lead customers engaged in vision, audio and voice applications are very excited about this effort,” said Steve Tateosian, Senior Vice President IoT Compute & Wireless at Infineon. “By integrating NVIDIA TAO in our PSOC Edge portfolio, we empower developers to create smarter and more efficient systems that work at the edge of the network and solve real-world challenges with speed and precision. This significantly speeds up time-to-market for ML enabled applications in industrial automation, medical, automotive, and smart IoT solutions.”
“NVIDIA TAO brings the latest advances in computer vision models and fine-tuning workflows to the far edge”, said Deepu Talla, Vice President of Robotics and Edge Computing at NVIDIA. “Infineon PSOC Edge’s integration of NVIDIA TAO greatly simplifies the development and deployment of customised AI across a range of devices.”
The integration of NVIDIA TAO features will become available for the entire PSOC Edge family along with a comprehensive development ecosystem, including tools, libraries, and documentation, to accelerate innovation and reduce time-to-market for AI-enabled applications.
