Machine Learning Interpretability: Why and How?

Details

Welcome to the Feb'20 chapter of Düsseldorf Data Science Meetup. In this event, Omayma Said will talk about Machine Learning Interpretability.

*** Agenda ***
• 18:30 - 19:00: Arrival, get a drink, snacks & socialize
• 19:15 - 20:00: Talk
• 20:00 - 20:15: Q&A
• 20:15 - Open End: Socialising

*** Machine Learning Interpretability: Why and How? ***
With the increasing adoption of machine learning-based solutions in different domains, systems that use black-box algorithms are getting used more often with the promise of providing better performance. However, this improvement in performance comes at the cost of interpretability, which introduces a barrier against wider adoption of such algorithms in crucial areas and raises the skepticism of the impacted individuals. This session will focus on the importance of interpretable machine learning, why it is crucial from technical and ethical perspectives and its current limitations. In addition, we will go over some of the relevant tools/packages (e.g. LIME, SHAPLEY) and discuss some real-life use cases.

*** About the Speaker ***
Omayma is a Senior Data Scientist with a background in electronics and telecommunication engineering. She worked in several roles where she dealt with different types of data, built data products, and previously led a data science team. In the world of data science, she is most interested in reproducible workflows, fairness in data products and explainable AI. She also enjoys teaching coding and data-science related skills and she is a certified instructor from The Carpentries and Rstudio.

*** Venue ***
Thanks to InVision (https://www.ivx.com) for hosting & sponsoring this edition of the Düsseldorf Data Science Meetup.
There will be food and drinks available.