YoVDO

Machine Learning Explainability & Bias Detection with Watson OpenScale

Offered By: Nicholas Renotte via YouTube

Tags

Machine Learning Courses IBM Watson Courses Model Interpretability Courses

Course Description

Overview

Learn how to leverage Watson OpenScale for machine learning explainability, debiasing, and drift detection in this comprehensive 23-minute tutorial video. Discover the process of setting up Watson OpenScale, viewing model performance metrics, debiasing machine learning predictions, and explaining and interpreting model predictions. Follow along as the instructor guides you through evaluating model performance, mitigating bias, conducting what-if scenario modeling, tracking model quality, and assessing model and data drift. Gain valuable insights into maintaining and improving deployed machine learning models, ensuring their performance, fairness, and interpretability.

Syllabus

- Start
- Explainer
- How it Works
- Setup Watson OpenScale
- Evaluating Model Performance
- Mitigating and Detecting Bias in ML Models
- Explaining and Interpreting Predictions
- What-If Scenario Modelling using OpenScale
- Tracking Model Quality
- Evaluating Model and Data Drift
- Wrap Up


Taught by

Nicholas Renotte

Related Courses

Machine Learning Interpretable: interpretML y LIME
Coursera Project Network via Coursera
Machine Learning Interpretable: SHAP, PDP y permutacion
Coursera Project Network via Coursera
Evaluating Model Effectiveness in Microsoft Azure
Pluralsight
MIT Deep Learning in Life Sciences Spring 2020
Massachusetts Institute of Technology via YouTube
Applied Data Science Ethics
statistics.com via edX