Learn how H2O.ai is lending AI expertise to combating COVID-19 challenges. > X
Search Close
Return to page

By using this website you agree to our use of cookies. Read H2O.ai’s privacy policy. Close icon

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.

Links:

“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

Brief Perspective on Key Terms and Ideas in Responsible AI

INTRODUCTION As fields like explainable AI and ethical AI have continued to develop in academia and

April 2, 2020 - by Benjamin Cox
Three Ways Data and AI is Helping Against COVID19

We are in the midst of a global crisis that epidemiologists have warned us about.

April 1, 2020 - by Niki Athanasiadou
Modelling Currently Infected Cases of COVID-19 Using H2O Driverless AI

In response to the wake of the pandemic called COVID-19, H2O.ai organized a panel discussion

March 30, 2020 - by Marios Michailidis
Deploying Models to Maximise the Impact of Machine Learning — Part 1

Introduction to the 4 key pillars of considerations for model deployment (1st part of a

March 29, 2020 - by Stefan Pacinda and John Spooner
Igniting the AI in Healthcare Community

Yesterday we held our first Community Discussion on AI in Healthcare. Our CEO and founder,

March 28, 2020 - by David Engler
COVID-19: Doing Good with Data + AI

During times of severe societal strain, individuals have historically shown an inclination to offer aid

March 26, 2020 - by David Engler and Marios Michailidis

Join the AI Revolution

Subscribe, read the documentation, download or contact us.

Subscribe to the Newsletter

Start Your 21-Day Free Trial Today

Get It Now
Desktop img

Thank you for your submission, please check your e-mail to set up your account

Thank you for your submission, please check your e-mail to set up your account

Thank you for your submission, please check your e-mail to set up your account