An Optimized Recurrent Unit for Ultra-Low Power Acoustic Event Detection with Justice Amoh Jr

Today, we're joined by Justice Amoh, a PhD student at Dartmouth's Thayer School of Engineering. Justice presented his work on "An Optimized Recurrent Unit for Ultra-Low Power Acoustic Event Detection." In our conversation, we discuss his goal of bringing low cost, high-efficiency wearables to market for monitoring asthma. We explore the many challenges of using classical machine learning models on microcontrollers, and how he went about developing models optimized for constrained hardware environments. We'd also like to wish Justice the best of luck as he should be defending his PhD any day now!