Understanding Out of Distribution Detection in Machine Learning

15min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

This chapter explores the critical concept of out of distribution (OOD) detection in machine learning, highlighting the challenges models face when exposed to new data that differs from their training sets. It emphasizes the importance of robust models in ensuring AI systems' performance and safety, particularly in high-stakes applications like self-driving cars and healthcare. The discussion includes methodologies for detecting OOD scenarios, the complexity of open set recognition, and the implications for model explainability.

A major challenge in applied AI is out-of-distribution detection, or OOD, which is the task of detecting instances that do not belong to the distribution the classifier has been trained on. OOD data is often referred to as “unseen” data, as the model has not encountered it during training.

Bayan Bruss is the VP of AI Foundations at Capital One and in this role he works with academic researchers to translate the latest research to address fundamental problems in financial services. Bayan joins the show with Sean Falconer to talk about OOD, the importance of bringing AI research to real world applications, and more.

Full Disclosure: This episode is sponsored by Capital One

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from information visualization to quantum computing. Currently, Sean is Head of Marketing and Developer Relations at Skyflow and host of the podcast Partially Redacted, a podcast about privacy and security engineering. You can connect with Sean on Twitter @seanfalconer.