How to Use AI Reliability to Identify and Predict Model Decay

Data Science Leaders

English - May 11, 2021 04:00 - 39 minutes - 72.3 MB - ★★★★★ - 82 ratings
Technology Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed

Previous Episode: An Introduction to Data Science Leaders, a Podcast for Daring Data Science Teams

Next Episode: How to Be a Truth-Seeking, Truth-Telling Partner in Data Science

What if we could predict how long our models will last in the field?

Is there a mathematical way to estimate mean time to failure for a specific model?

In this episode, Dave Cole is joined by Celeste Fralick, Chief Data Scientist at McAfee, to discuss AI reliability and how it can help predict model decay.

Celeste also explained:

- What AI reliability measures

- Processes to put in place to measure AI reliability

- The difference between DevOps and MLOps at McAfee

- How adversarial machine learning works

- How to build out a more diverse data science team

Tune in on Apple Podcasts, Spotify, our website, or wherever you listen to podcasts.

Listening on a desktop & can’t see the links? Just search for Data Science Leaders in your favorite podcast player.