Module 7 - Machine Learning Operations


Back to Package

In this module, you will learn about the basics of machine learning operations, known as model ops or ML Ops. Model operations covers vital areas related to running models in production environments. Key topics include production model deployment, production model lifecycle management, and production model governance. In each area, we will discuss the issues and solutions as organizations move from manual processes to a more managed and governed approach.

 Learning Outcomes
  • Describe the roadblocks for production models in today's environment
  • What are the functional areas of production operations for machine learning models
  • Distinguish between the value of taking a managed and governed approach to machine learning production issues

Key:

Complete
Failed
Available
Locked
Session 1(Slides & Replay): MLOps Overview
Click on View to access the replay and the slides
Click on View to access the replay and the slides Slides and Replay of our first AI Foundations Course session Module 7.
Quiz 1: MLOps Overview
10 Questions  |  2 attempts  |  8/10 points to pass
10 Questions  |  2 attempts  |  8/10 points to pass
Session 2(Slides & Replay): MLOps Deep Dive
Click on View to access the replay and the slides
Click on View to access the replay and the slides Slides and Replay of our second AI Foundations Course session Module 7.
Quiz 2: MLOps Deep Dive
10 Questions  |  2 attempts  |  8/10 points to pass
10 Questions  |  2 attempts  |  8/10 points to pass
You must be logged in to post to the discussion
  • RC

    Hi, 

    I was wondering if it would be possible for me to retake quiz 1 for MLops Overview. I wasn't able to get the score I wanted on the quiz which has resulted in me not being able to take the final exam. I was hoping to test my knowledge from what I had gained throughout this course, and see if I had fully soaked in all the material from the course cohesively. Thank you. 

    Reply
  • KS

    In the Life-cycle management workflow, Refit model is pushed to warm up test in prod. can I assume the model will be pushed to Validation if the Fail over/Troubleshoot step prior to Refit confirms a rollback scenario ? Also, this will be the case if the Refit model requires significant validation due to the amount of fix made (algorithm changes or data source changes etc)

    Reply
  • RS

    Slide 30, part 2:

    MLOps should maintain a full (trace ? control ? of ) all models used in production and training data (if possible)

    trace ? control ? of missing in the phrase.

    Reply
  • KS

    Hi Rino, I believe it is the keyword "History" that got left out in the slide. Complete history should be required if there will be a need to rollback the model to older version for investigation and update

    Reply