Evolving AI Systems Gracefully with Stefano Soatto

EPISODE 502
WATCH
Play Video
Join our list for notifications and early access to events

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.
Connect with Stefano
Read More

Thanks to our sponsor Amazon Web Services

AWS offers a broad array of services and infrastructure at all three layers of the machine learning technology stack. More than 100,000 customers trust AWS for Machine Learning, and the company aims to put ML in the hands of every developer, data scientist, and enthusiast with newly announced offerings like Amazon CodeWhisperer, a new ML-powered pair programmer that helps developers improve productivity by reducing the time to build software applications significantly.

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

And also be sure to check out stage.twimlai.net/go/sagemaker to sign up for SageMaker Studio Lab.

Amazon Web Services Logo

More from TWIML

Leave a Reply

Your email address will not be published.