XAI: Learning Fairness with Interpretable Machine
An AI ethics event on bias and unfair representations and how to counteract the challenges that come along.
The deployment of large-scale machine learning systems trained on increasing amounts of data has shown to have a big impact on a range of industries and thus, on our everyday lives. With that comes the need and obligation for explainable AI, interpretability and fairness. In this event we’ll have a closer look at bias and unfair representations and how to counteract the challenges that come along.
10-min: Trends in Artificial Intelligence and Data Fairness: Tim Denley, Director of Board, Chief Solutions Officer, KPMG Ignition Tokyo
A talk on KPMG’s view on data reliability and results along with our effort at KPMG Ignition Tokyo.
30-min: Learning Fairness with Interpretable Machine Learning: Serg Masis, Author of “Interpretable Machine Learning with Python”; Climate & Agronomic Data Scientist, Syngenta
An overview of many methods employed to detect and mitigate bias and place guardrails to ensure fairness with Python examples
This event will be moderated by Haiyang Peng, a Senior Scientist at KPMG Ignition Tokyo.
Special thanks to KPMG Ignition Tokyo and Machine Learning Tokyo for co-hosting the event with us!
How to join the event:
If you register, you will receive the livestream link email 3 days before the event.
Can’t attend the live YouTube event? Don’t worry. Register now to get the recorded session.
Tim Denley is focused on digital and innovative transformation utilizing a broad range of strategic business, technology and communication skills. He has been leading various digital transformation teams for over ten years and is dedicated to building the best possible environment where team members with high skills, which are indispensable for realizing digital transformation, can fully exercise their potential abilities.
Serg Masis is a Data Scientist in agriculture with a background in entrepreneurship and web/app development, and the author of the book “Interpretable Machine Learning with Python”. Passionate about ML interpretability, responsible AI, behavioral economics, and causal inference. To learn more about Serg, visit https://serg.ai