FREE TRAINING | OCTOBER 11-15, 2021 | 4PM PT / 7PM ET

ML Fairness

Mini-Bootcamp

In this free 4-day bootcamp, you'll gain a structured overview of common sources of bias and frameworks for reasoning about fairness in applied machine learning settings. There are two lectures and two hands-on labs that provide examples of how standard ML algorithms fail in real-world environments.

Seats are limited, so save your spot today!

Save My Spot

What you'll Learn:

This bootcamp follows the curriculum of UC Berkeley's ML Fairness Bootcamp. Find details about the bootcamp here.

01

Lecture 1: How to Identify Bias

ML algorithms can exhibit bias against people whose characteristics have served as the basis for systematically unjust treatment in the past; see how this happens in industry.

02

Lab 1: Racial Bias in Healthcare

Discover how this algorithm embeds a bias against Black patients, undervaluing their medical risk relative to White patients.

03

Lecture 2: Measuring & Mitigating Bias

What are quantitative indicators of bias? How do we make biased algorithms less harmful?

04

Lab 2: Mitigating Gender Bias in Hiring

In this lab, we take a dataset in which prior hiring decisions have adversely impacted women, and show how applying fairness constraints can mitigate the effect of this.

MEET YOUR INSTRUCTOR

Understand How Unfairness Creeps In

Since 2016, Ayodele Odubela has helped Data Science teams design, develop, and implement machine learning models. She's spent the past two years researching fairness issues in machine learning. In this bootcamp, she will be sharing methods for you identify and mitigate bias in algorithms.