February 20th, 2020

Interview with Patrick Hall | Machine Learning, H2O.ai & Machine Learning Interpretability

RSS icon RSS Category: Data Science, Driverless AI, Explainable AI, Machine Learning Interpretability, Makers

Audio Link:

In this episode of Chai Time Data Science, Sanyam Bhutani interviews Patrick Hall, Sr. Director of Product at H2O.ai. Patrick has a background in Math and has completed a MS Course in Analytics.

In this interview they talk all about Patrick’s journey into ML, ML Interpretability and his journey at H2O.ai, how his work has evolved over the years. They talk a lot about MLI, ML Explainability and Model Debugging.

They also talk about how these ideas are implemented inside of h2o.ai and how can someone bring these ideas to their pipelines.


“Real-World Strategies for Model Debugging”: https://medium.com/@jphall_22520/stra…

An Intro to MLI Book: https://www.h2o.ai/wp-content/uploads…

“Why you should care about debugging machine learning models”: https://www.oreilly.com/radar/why-you…

“Proposed Guidelines for the Responsible Use of Explainable Machine Learning”: https://arxiv.org/pdf/1906.03533.pdf

Show Notes/Timings:

03:14: When did you discover your passion for ML?

07:26: Current job and a day in your life?

10:31: AutoML to replace humans or Humans in the loop?

12:12: Did you always enjoy teaching?

14:25: Journey at H2O.ai

20:43: Why is MLI important?

24:06: Is MLI ready to use? Is ML Still a black box?

32:27: At what stages should we look into MLI?

43:16: Can a creator of MLI tools also possibly introduce biases?

46:44: What interests you in research?

52:06: Best advice to someone just starting their journey into ML and just starting to explore MLI?

About the Author

Sanyam Bhutani

Sanyam Bhutani is a Machine Learning Engineer and AI Content Creator at H2O.ai.

He is also an inc42, Economic Times recognized Machine Learning Practitioner. (link to the interviews: inc42, Economic Times)

Sanyam is an active Kaggler where he is a Triple Tier Expert, ranked in Global Top 1% in all categories as well as an active AI blogger on the medium, Hackernoon (Medium Blog link) with over 1 Million+ Views overall.

Sanyam is also the host of Chai Time Data Science Podcast where he interviews top practitioners, researchers, and Kagglers.

You can follow him on Twitter or subscribe to his podcast.

Leave a Reply

AI-Driven Predictive Maintenance with H2O Hybrid Cloud

According to a study conducted by Wall Street Journal, unplanned downtime costs industrial manufacturers an

August 2, 2021 - by Parul Pandey
What are we buying today?

Note: this is a guest blog post by Shrinidhi Narasimhan. It’s 2021 and recommendation engines are

July 5, 2021 - by Rohan Rao
The Emergence of Automated Machine Learning in Industry

This post was originally published by K-Tech, Centre of Excellence for Data Science and AI,

June 30, 2021 - by Parul Pandey
What does it take to win a Kaggle competition? Let’s hear it from the winner himself.

In this series of interviews, I present the stories of established Data Scientists and Kaggle

June 14, 2021 - by Parul Pandey
Snowflake on H2O.ai
H2O Integrates with Snowflake Snowpark/Java UDFs: How to better leverage the Snowflake Data Marketplace and deploy In-Database

One of the goals of machine learning is to find unknown predictive features, even hidden

June 9, 2021 - by Eric Gudgion
Getting the best out of H2O.ai’s academic program

“H2O.ai provides impressively scalable implementations of many of the important machine learning tools in a

May 19, 2021 - by Ana Visneski and Jo-Fai Chow

Start your 14-day free trial today