Production Machine Learning Monitoring: Outliers, Drift and Explainers


 Tuesday 1st March, 5pm GMT/12pm ET 

The lifecycle of a machine learning model only begins once it’s in production. In this webinar, Alejandro Saucedo, Director of Engineering at Seldon, will present an end-to-end example showcasing best practices, principles, patterns and techniques around monitoring of machine learning models in production. We will show how to adapt standard microservice monitoring techniques towards deployed machine learning models, as well as more advanced paradigms including concept drift, outlier detection and AI explainability.

Join this webinar to learn how to:

  • Train an image classification machine learning model from scratch.
  • Deploy it as a microservice in Kubernetes.
  • Introduce a broad range of advanced monitoring components, including outlier detectors and drift detectors, AI explainers and metrics servers.
  • Manage architectural patterns designed to work efficiently across hundreds or thousands of heterogeneous machine learning models.

© 2022 Seldon Technologies. All Rights Reserved.