Build GenAI Apps from Scratch — UCSB PaCE Certificate Program
Most AI Pilots Fail to Scale. MIT Sloan Teaches You Why — and How to Fix It
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore an open-source platform for serving and monitoring machine learning models at scale in this 29-minute talk from Databricks. Learn about KFServing, Kubeflow's model serving framework, and how it integrates with the Hopsworks Online Feature Store to enrich feature vectors. Discover the advantages of using Spark and Spark Streaming for continuous model monitoring, including data drift detection and performance analysis. Gain insights into implementing MLOps practices, automating repetitive tasks, and improving interoperability between tools. Watch a live demonstration of the platform in action and understand how to leverage these technologies for more effective model deployment and monitoring in production environments.
Syllabus
Intro
KFServing
Model Modeling
Online Monitoring
Data Validation
Data Validation Example
Demo
Questions
Taught by
Databricks