Edge Machine Learning: Possibilities and Creative Uses

Abstract:
Generative AI, like ChatGPT and DALL-E, is all the rage right now, but AI goes way beyond turning phrases into pictures. Edge AI (and its subset, tiny machine learning) is the process of running AI algorithms on edge devices, such as smartphones, wearables, single board computers, and embedded systems. The process to run such algorithms on resource-constrained devices is tricky, as it requires accurately scoping the problem and optimizing the algorithm, code, and hardware.

This talk will cover why running AI on small devices is a good idea along with some pitfalls. Much of edge machine learning (ML) focuses on solving technical problems related to bandwidth, latency, energy usage, reliability, and privacy. However, edge ML has enabled some incredibly creative projects, including magic wands, homemade smart speakers, and artificial noses that make perfect toast. Recommendations on getting started with edge ML will be provided.

Bio:
Shawn is a machine learning DevRel engineer, instructor, and university program manager at Edge Impulse. He creates compelling technical videos, courses, and workshops around edge machine learning that inspire engineers of all skill levels. Shawn is an advocate for enriching education through STEM and believes that the best marketing comes from teaching. He can be found giving talks, running workshops, and swing dancing in his free time. https://shawnhymel.com/