This month's workshop session:
"Removing Unfair Bias in Machine Learning" by Svetlana Levitan, IBM
Extensive evidence has shown that AI can embed human and societal bias and deploy them at scale. And many algorithms are now being re examined due to illegal bias. So how do you remove bias & discrimination in the machine learning pipeline? In this webinar you’ll learn the debiasing techniques that can be implemented by using the open source toolkit AI Fairness 360.
AI Fairness 360 (AIF360) is an extensible, open source toolkit for measuring, understanding, and removing AI bias. AIF360 is the first solution that brings together the most widely used bias metrics, bias mitigation algorithms, and metric explainers from the top AI fairness researchers across industry & academia. In this webinar you’ll learn:
· How to measure bias in your data sets & models
· How to apply the fairness algorithms to reduce bias
How to apply a practical use case of bias measurement & mitigation in a data-driven medical care management scenario
What you'll learn:
An introductory look at how bias & discrimination can arise within modern machine learning techniques and the methods that can be implemented to tackle those challenges.
Learn how to evaluate the metrics using the open-source AI Fairness 360Toolkit (http://aif360.mybluemix.net/) to check for fairness and mitigate machine learning model bias.
Prerequisites:
Basic knowledge of machine learning
Experience using Python (not required)
Materials Required Prior to Class:
Laptop with Python 3 installed
Please install the Python packages before the class: https://github.com/IBM/AIF360/wiki/OSCON-PORTLAND-2019and https://github.com/ibm/aif360
Agenda:
7:00p - 7:15p Announcements and introductions
7:15p - 9:00pm Workshop with IBM
Organized by Six Feet Up, the Indianapolis Python Meetup (“IndyPy”) is a leading national group promoting the Python programming language and connecting the Python community. IndyPy draws Python enthusiasts from the entire Midwest for regular events. In 2019, the group celebrated 12 years of success with over 1,800+ members.
Interested in sponsoring IndyPy? Let's talk
More info is at http://indypy.org