Intel and Udacity on Thursday launched a new nanodegree program to help developers learn how to build and deploy deep learning models at the edge. The Intel Edge AI for IoT Developers Nanodegree Program uses the Intel Distribution of OpenVINO toolkit and is designed to accelerate the development and deployment of AI-powered edge devices.
As data collection and processing moves to the edge, developing edge AI solutions should be valuable in a range of industries, from health care to manufacturing. Yet as Intel's Jonathan Ballon noted, developing and deploying AI models at the edge requires particular knowledge that most developers may not have.
"Historically, students have learned how to build and deploy deep learning models for the cloud," Ballon, GM of Intel's Internet of Things Group, said in a statement. "With Udacity, we are training AI developers to go where the data is generated in the physical world: the edge. Optimizing direct deployment of models on edge devices requires knowledge of unique constraints like power, network bandwidth and latency, varying compute architectures and more. The skills this course delivers will allow developers – and companies that hire them – to implement learnings on real-world applications across a variety of fields."
The new program is expected to take about three months to complete. It will introduce students to the OpenVINO (Open Visual Inference & Neural network Optimization) toolkit, which enables developers to deploy pre-trained deep learning models through a high-level C++ or Python inference engine API integrated with application logic. Students will complete three real-world projects that will be reviewed and approved by Udacity's reviewer network.
Students who successfully complete the program will receive a Udacity graduation certificate.
Udacity and Intel are also offering a subset of the program's content for free, via the new Intel Edge AI Fundamentals with OpenVINO course.