Applied AI Auditing in Python
Offered By: LinkedIn Learning
Course Description
Overview
Learners how to conduct audits to quantify unfairness and disparities to uncover bias and develop fairer AI systems.
Syllabus
Introduction
- Get responsible with AI: Auditing AI systems in Python
- What you should know
- Using the exercise files and datasets
- AI auditing for compliance and fairness
- AI audit stakeholders
- Localized fairness and compliance
- How to collect benchmark datasets
- Ethical and inclusive data collection
- Explore a dataset for representation
- Data auditing example
- Challenge: Audit a dataset
- Solution: Methods for increasing representation in data
- Tools for AI audits
- Scoping an AI audit
- Model audit setup
- Audit your classifier for fairness
- Challenge: Audit a classifier
- Solution: Audit a classifier
- Red teaming
- Error analysis
- Challenge: Error analysis
- Solution: Error analysis
- Making audit recommendations
- Sharing audit results and increasing accountability
- Algorithmic recourse
- Algorithmic design history file
- Thanks for watching
Taught by
Ayodele Odubela
Related Courses
Artificial Intelligence Algorithms Models and LimitationsLearnQuest via Coursera Artificial Intelligence Data Fairness and Bias
LearnQuest via Coursera Towards an Ethical Digital Society: From Theory to Practice
NPTEL via Swayam Human Factors in AI
Duke University via Coursera Identify principles and practices for responsible AI
Microsoft via Microsoft Learn