Machine Learning Porto #5 - Avoiding the Machine Learning Blackbox

Hey folks!

After a summer break, we are back!

To kick off this new season we have the pleasure to have Miguel José Monteiro who is going to talk to us about Explainability in ML and take us through SHAP as a tool for explainability.
We are also happy to be running this event on the amazing Fábrica Nortada who kindly accepted to host us.

------------------------------------------
AGENDA

19:00 - 👋 Meet & Greet
19:15 - 🎙 Avoiding the Machine Learning Blackbox
20:30 -🕴Networking

------------------------------------------
TALKS & SPEAKERS

Title:
Avoiding the Machine Learning Blackbox

Abstract:
Nowadays more than ever, companies and researchers who work on Machine Learning face one huge challenge: “blackbox algorithms”. These algorithms can be loosely defined as algorithms whose output is not easily interpretable or is non-interpretable altogether, meaning you get an output from an input but you don’t understand why. In this talk, I will talk a bit about the topic of explainability in Machine Learning and I will explore SHAP as a tool for explainability.

About the speaker:
Miguel José Monteiro is Team Lead on Nanovare, a medtech startup bringing computer vision to human fertility assessment. He holds an MSc in Biomedical Engineering from FEUP (that he currently doesn't give that much use) and has worked in Data Science since 2014 (back when Matlab was "cool"). Besides that, Miguel is part of Data Science Portugal and Data Science for Social Good Portugal and is a pro in not having enough time in his schedule to fit any more activities.