Deploying ML models on edge devices offers several benefits such as reducing data traffic between the edge and the cloud, decreasing latency, and safeguarding privacy by avoiding the transmission of raw data to the cloud. Recent advancements on MCU hardware technology and ML model compression have enabled the deployment of lightweight ML models on MCUs with impressive performance. This talk introduces a few key examples of MCU-based ML applications, showcasing their practical implementation. Additionally, it highlights the significant acceleration of ML performance achievable with Neural Processing Unit enabled MCU.
Schedule
Timezone: PDT
Empowering the Edge: Practical Applications of Embedded Machine Learning on MCUs
Jongmin LEE, Machine Learning Architecture Engineer
NXP
Jongmin LEE, Machine Learning Architecture Engineer
NXP
Jongmin Lee is a Machine Learning Architecture Engineer at NXP semiconductors. Throughout his career at NXP, he has primarily focused on developing MCU-based machine learning solutions, and currently, his area of concentration is on advancing the architecture of neural processing unit. He earned his Ph.D. degree in Electrical Engineering from Arizona State University, Tempe, in 2017. He was a research assistant at the Sensor, Signal, and Information Processing (SenSIP) center at Arizona State University.
Schedule subject to change without notice.