MLOps Essentials: Monitoring Model Drift and Bias

Focused View

Kumaran Ponnambalam

1:05:13

13 View

01 - Introduction

01 - The need for model monitoring.mp4

00:40

02 - Setting up the exercise files.mp4

02:29

02 - 1. Introduction to Model Monitoring

01 - ML models in production.mp4

02:36

02 - Challenges with serving models in production.mp4

01:44

03 - Metrics to monitor.mp4

03:26

04 - Data for model monitoring.mp4

01:35

03 - 2. Model Drift Basics

01 - Introduction to model drift.mp4

04:49

02 - Concept drift.mp4

01:34

03 - Feature drift.mp4

02:26

04 - What causes drift.mp4

02:01

05 - Drift remediation process.mp4

01:19

04 - 3. Detecting Model Drift

01 - Detecting concept drift.mp4

02:08

02 - Concept drift detection example.mp4

02:48

03 - Detecting feature drift.mp4

01:47

04 - Feature drift detection example.mp4

01:54

05 - Detecting drift in text and images.mp4

02:59

06 - Software for drift detection.mp4

00:52

05 - 4. Drift Monitoring Process and Best Practices

01 - Drift monitoring pipeline.mp4

01:57

02 - Analyzing drift trends.mp4

02:20

03 - Discovering root causes for drift.mp4

02:07

04 - Retraining to overcome drift.mp4

02:01

06 - 5. Introduction to Model Bias

01 - Fairness and bias.mp4

02:05

02 - Fairness in ML.mp4

01:20

03 - Sources of ML bias.mp4

01:35

04 - Protected attributes.mp4

01:23

05 - Demographic parity.mp4

02:12

07 - 6. Bias Detection and Best Practices

01 - Bias detection techniques.mp4

02:31

02 - Equal opportunity score.mp4

02:53

03 - EOS example.mp4

01:58

04 - Bias detection software.mp4

00:48

05 - Overcoming bias in ML.mp4

02:21

08 - Conclusion

01 - Next steps.mp4

00:35

Description

As more and more ML models are developed and deployed, the need arises to ensure that the models are effective and safe and that they perform as desired. Model monitoring, a core function of MLOps, helps data scientists and MLOps engineers to meet this need. In this course, data analytics expert Kumaran Ponnambalam discusses the types of monitoring needed for ML models. He deep dives into model drift monitoring and bias. For model drift, Kumaran goes over the types of drift monitoring and their causes. He explains different techniques for drift monitoring and how to execute them in python using open source libraries. For bias, Kumaran highlights various sources of bias and their impact. He also analyzes bias in python with open source libraries. Finally, he recommends some best practices for drift and bias monitoring.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

Kumaran Ponnambalam

Instructor's Courses

A seasoned veteran in everything data, with a reputation for delivering high performance database and SaaS applications and currently specializing in leading Big Data Science and Engineering efforts

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.