Mar 15–18, 2020

Debugging machine learning models

Navdeep Gill (H2O.ai)
2:35pm3:15pm Tuesday, March 17, 2020
Location: 210 C/G

Who is this presentation for?

  • Data scientists

Level

Intermediate

Description

Prediction by machine learning models is fundamentally the execution of a computer program. In this case, the rules of the computer program are learned by the computer itself from training data instead of being programmed by a human. Like all good programs, machine learning models should be debugged to discover and remediate errors.

When the debugging process increases accuracy in holdout data, increases transparency into model mechanisms, decreases or identifies hackable attack surfaces, or decreases disparate impact, this debugging process also enhances trust and interpretability in model mechanisms and predictions. Navdeep Gill identifies several standard techniques in the context of model debugging—disparate impact, residual, and sensitivity analysis—and introduces novel applications such as global and local explanation of model residuals.

Prerequisite knowledge

  • A basic understanding of machine learning

What you'll learn

  • Experience debugging machine learning models
Photo of Navdeep Gill

Navdeep Gill

H2O.ai

Navdeep Gill is a senior data scientist and software engineer at H2O.ai, where he focuses mainly on machine learning interpretability and had focused on GPU-accelerated machine learning, automated machine learning, and the core H2O-3 platform. Previously, Navdeep focused on data science and software development at Cisco and was a researcher and analyst in several neuroscience labs at California State University, East Bay, University of California, San Francisco, and Smith Kettlewell Eye Research Institute. Navdeep earned an MS in computational statistics, a BS in statistics, and a BA in psychology (with a minor in mathematics) from California State University, East Bay.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

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

Become a sponsor

For information on exhibiting or sponsoring a conference

pr@oreilly.com

For media/analyst press inquires