Beginning with Endpoint Intelligence, Renesas aims to contribute to the realization of an eco-friendly, smart society that supports safer and healthy living in areas where this cannot be solved simply by using big data at clouds. With its flexible and scalable embedded artificial intelligence (e-AI) concept, Renesas offers a future proof real-time, low power AI processing solution that is unique in the industry and addresses the specific needs for artificial intelligence in embedded devices at the endpoint.
The Renesas e-AI development environment makes it possible to implement learned Deep Neural Network (DNN) results onto an MCU/MPU in conformance with an e² studio C/C++ project.
An e-AI demonstration experiment revealed that e-AI has greatly improved detection precision with regards to facility abnormalities that previously could only be properly judged by a skilled technician or operator.
Renesas' e-AI Translator is a tool that converts and imports the inference processing of neural network models which have been trained in an open-source deep-learning framework into source code files for the e² studio IDE.