How to detect silent failures in ML models

About the talk

Artificial intelligence algorithms deteriorate and fail silently over time, impacting the business’ bottom line. The talk is focused on learning how you should be monitoring machine learning in production. It is a conceptual and informative talk addressed to Data Scientists & Machine Learning Engineers. We'll learn about the types of silent failures, and how to detect and address them.

This talk will cover

  • Build an understanding of why and how to monitor machine learning in production.
  • Understand the taxonomy of failures based on use cases, data, characteristics of systems they interact with, and human involvement.
  • Learn the statistical and algorithmic tools used to deal with failures, as well as their applications and limits.
  • Understand real-life use cases that show the importance of ML monitoring in one of the biggest industries.
Programming & Development

About the speaker

Wojtek Kuberski

Wojtek Kuberski is a co-founder of NannyML, a startup for monitoring ML models in production. He holds a Master's Degree in AI and previously founded and grew an AI consultancy. He likes tennis, chess, and food.

Want a high-income, remote career in Programming?

Join Arc and receive offers from high-growth tech startups paying from $60,000 to 175,000 USD!

Discussion 

Loading...