14–17 Oct 2019

Concepts and tools for fairness, explainability, and robustness in machine learning

Ilya Feige (Faculty)
14:3515:15 Thursday, 17 October 2019
Location: King's Suite - Balmoral
Average rating: *****
(5.00, 2 ratings)

Who is this presentation for?

  • Heads of data science, data scientists, and ML engineers

Level

Beginner

Description

Ilya Feige details the AI safety concerns—fairness, robustness, and explainability—that are already relevant for ML models in use today.

Fairness ensures that a model’s predictions do not unethically discriminate against protected groups. This is a subtle matter, since unfair biases can exist in the data used to train the model as well as in the model’s own decision-making algorithm; moreover, precise definitions of such unfair biases are often mathematically contradictory and not widely agreed upon.

Robustness builds expectations for how an ML model will behave upon deployment in the real world. It addresses the questions of estimating uncertainties in its predictions and whether or not the model is robust to perturbed data.

Explainability tackles the question of how an ML model makes its predictions. An improved understanding of the model is essential for detecting, avoiding, and removing its failure modes; for earning public trust in the algorithm; and for introducing effective policies to regulate the technology.

Ilya demonstrates the AI safety tools developed at Faculty so you gain a detailed understanding of its models from these three perspectives. You’ll leave with the knowledge to deploy fair, robust, and explainable models, with a focus on concepts and examples.

What you'll learn

  • Discover a set of easy-to-use tools that allow you to expose, study, and correct misbehavior in machine learning models
Photo of Ilya Feige

Ilya Feige

Faculty

Ilya Feige is the director of AI at Faculty, where he leads the company’s research and development efforts and ensures that cutting-edge machine learning is used across all Faculty’s commercial data science projects. Previously, Ilya worked at McKinsey & Company, helping to deploy artificial intelligence for some of the world’s largest brands. He’s also an honorary senior research fellow in artificial intelligence at UCL. Ilya was awarded the Goldhaber prize for the best PhD in theoretical physics from Harvard University, and the Governor General’s award for the single highest ranked undergraduate student at McGill University.

Comments on this page are now closed.

Comments

Dany Daher | Technical Program Manager
5/11/2019 5:50 GMT

Hi Ilya, I missed your talk at the conference. Do you mind sharing the presentation? Thanks, Dany

  • Intel AI
  • O'Reilly
  • Amazon Web Services
  • IBM Watson
  • Dell Technologies
  • Hewlett Packard Enterprise
  • AXA

Contact us

confreg@oreilly.com

For conference registration information and customer service

partners@oreilly.com

For more information on community discounts and trade opportunities with O’Reilly conferences

aisponsorships@oreilly.com

For information on exhibiting or sponsoring a conference

pr@oreilly.com

For media/analyst press inquires