Скачать или смотреть Session 13: ML Foundations Course - Machine Learning Interpretability with H2O-3

This video was recorded on October 29, 2020

Slides from the presentation are available here: https://www.h2o.ai/community/viewdocu...

To find additional videos on ML courses, earn badges, join the courses at H2O.ai Learning Center: https://training.h2o.ai/products/mach...

OUTLINE:

0:00 - ML Foundations
1:20 - Overview
6:41 - H2O-3 Model Explainability Toolkit
11:24 - Model Explainability Code Example
42:40 - Quick Recap
44:40 - What's Next?

Description:

In this session, we will explore various machine learning interpretability (MLI) techniques to explain an H2O-3 Model.

By the end of this session you will be able to examine an ML model's variable/feature importance, build partial dependence and individual conditional expectation (ICE) plots for global and local visualizations of a model's predictions, and reason code generating techniques.
And lastly, generate documentation for the model produced.

Speaker:

Jo-fai Chow is a Senior Data Science Evangelist at H2O.ai