The Learning Curve: Debugging Model Performance with Scale Nucleus

Oct 30th @ 7PM Coordinated Universal TimeOnline

About The Webinar

In this Tech Talk, we will show how you can achieve the concept of “Operation Vacation” for the models you create, and make sure that the model is testing the subsets that you actually care about with Scale’s latest product, Scale Nucleus.

Using PandaSet, a multimodal dataset for autonomous driving, we will demonstrate how you can easily debug model performance and automatically refine your model. In the process we’ll also dive into Nucleus’s features to show how to curate sub datasets and edge cases easily with custom metrics, image similarity search, and auto-pivot, automatically augmenting the data collection to accelerate machine learning training process.

Presented By

Elliot Branson

Elliot Branson

Elliot Branson is a Director of Engineering at Scale AI, where he leads the Machine Learning, 3D, and Platform teams as well as the development of new products such as Nucleus and GIS. Prior to Scale AI, Elliot founded and led the perception and AI team at Cruise Automation and also worked on Project Tango at Google.

The Learning Curve: Debugging Model Performance with Scale Nucleus