Evolving AI Systems Gracefully with Stefano Soatto

EPISODE 502
|
JULY 19, 2021
Watch
Play
Follow

Share
Don't Miss an Episode!  Join our mailing list for episode summaries and other updates.

About this Episode

Today we're joined by Stefano Soatto, VP of AI applications science at AWS and a professor of computer science at UCLA. Our conversation with Stefano centers on recent research of his called Graceful AI, which focuses on how to make trained systems evolve gracefully. We discuss the broader motivation for this research and the potential dangers or negative effects of constantly retraining ML models in production. We also talk about research into error rate clustering, the importance of model architecture when dealing with problems of model compression, how they've solved problems of regression and reprocessing by utilizing existing models, and much more.

About the Guest

Stefano Soatto

Amazon Web Services (AWS)

Connect with Stefano

Thanks to our sponsor Amazon Web Services

You know AWS as a cloud computing technology leader, but did you realize the company offers a broad array of services and infrastructure at all three layers of the machine learning technology stack? AWS has helped more than 100,000 customers of all sizes and across industries to innovate using ML and AI with industry-leading capabilities and they’re taking the same approach to make it easy, practical, and cost-effective for customers to use generative AI in their businesses. At the bottom layer of the ML stack, they’re making generative AI cost-efficient with Amazon EC2 Inf2 instances powered by AWS Inferentia2 chips. At the middle layer, they’re making generative AI app development easier with Amazon Bedrock, a managed service that makes pre-trained FMs easily accessible via an API. And at the top layer, Amazon CodeWhisperer is generally available now, with support for more than 10 programming languages.

To learn more about AWS ML and AI services, and how they’re helping customers accelerate their machine learning journeys, visit twimlai.com/go/awsml.

Resources