SSUP collaboration: SFSU's On-Device Machine Learning Course with Spresense
At the intersection of academia and industry, Sony is proud to highlight our dynamic collaboration with the San Francisco State University (SFSU), School of Engineering, through the Sensing Solution University Collaboration Program (SSUP). This partnership has led to an exciting development – the introduction of the graduate course "On-Device Machine Learning" at SFSU.
As part of our collaboration, SFSU has designed a graduate/senior undergraduate course that not only leverages Sony's Spresense technology but also imparts invaluable knowledge at the intersection of machine learning and edge computing. The SFSU team aims to utilize Sony’s Spresense microcontroller board to develop efficient deep-learning algorithms for real-time high-density surface electromyography (HD-EMG) signal processing.
Within the course, students not only understand the fundamentals of on-device machine learning but also witness its transformative power in real-world applications. Sony's Spresense microcontroller allows for the execution of intelligent tasks independently, minimizing reliance on external servers and amplifying privacy, security, and power efficiency. SFSU students will be offered practical opportunities to learn how to build, train, optimize, and deploy deep learning models that can run on low-power edge devices, like Spresense.
On-device machine learning (sometimes called TinyML) refers to the deployment of machine learning models directly on edge devices, such as smartphones, IoT devices, and microcontrollers. This shift enables real-time processing and decision-making on the device, reducing the need for constant internet connectivity and reliance on remote servers.
The SSUP program provides students with essential resources such as Sony Spresense edge devices, camera boards, extension boards, and more to support their course projects. Through this partnership and the On-Device Machine Learning course, we are cultivating a new generation of innovators who will drive the next wave of advancements in embedded AI. We eagerly anticipate the innovative applications and discoveries that will emerge from the minds of these future pioneers!