226. Unsupervised Learning Makes Scalable Autonomy a Reality SAE Tomorrow Today

Artificial intelligence that teaches itself? That’s the gist of unsupervised learning. And it offers far-reaching implications for the future autonomous driving—and much more.
.
As a pioneer in unsupervised learning, Helm.ai employs an AI-first approach to building autonomous driving software using an in-house unsupervised learning technology called Deep Teaching which leverages insights from applied mathematics and compressive sensing.
.
Deep Teaching enables Helm.ai to train on vast volumes of data more efficiently without the need for large scale fleets or human annotation, moving the world closer to fully autonomous self-driving systems. The company licenses their software to automakers for high-end ADAS L2+/L3 products and uses the same scalable AI approach for L2/L3 ADAS through L4.
.
To learn more about this exciting breakthrough, we sat down with Vlad Voroninski, CEO & Co-Founder of Helm.ai, to discuss unsupervised learning, Deep Teaching, and the future of autonomous driving.
.
We’d love to hear from you. Share your comments, questions and ideas for future topics and guests to podcast@sae.org. Don’t forget to take a moment to follow SAE Tomorrow Today—a podcast where we discuss emerging technology and trends in mobility with the leaders, innovators and strategists making it all happen—and give us a review on your preferred podcasting platform.
. 
Follow SAE on LinkedIn, Instagram, Facebook, Twitter, and YouTube.
Follow host Grayson Brulte on LinkedIn, Twitter, and Instagram.