19 min listen
Real world model explainability with Rayid Ghani - TWiML Talk #283
FromThe TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Real world model explainability with Rayid Ghani - TWiML Talk #283
FromThe TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
ratings:
Length:
51 minutes
Released:
Jul 18, 2019
Format:
Podcast episode
Description
Today we’re joined by Rayid Ghani, Director of the Center for Data Science and Public Policy at the University of Chicago. Rayid’s goal is to combine his skills in machine learning and data with his desire to improve public policy and the social sector. Drawing on his range of experience from the corporate world to Chief Scientist for the 2012 Obama Campaign, we delve into the world of automated predictions and explainability methods. Here we discuss: How automated predictions can be helpful, but they don’t always paint a full picture When dealing with public policy and the social sector, the key to an effective explainability method is the correct context Machine feedback loops that help humans override the wrong predictions and reinforce the right ones Supporting proactive intervention through complex explanability tools
Released:
Jul 18, 2019
Format:
Podcast episode
Titles in the series (100)
This Week In Machine Learning & AI - 5/20/16: AI at Google I/O, Amazon's Deep Learning DSSTNE: This Week In Machine Learning & AI - May 20, 2016… by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)