Algorithmic bias and explainability in machine learning with tensorflow (Alejandro Saucedo)

A practical guide towards explainability and bias evaluation in machine learning - Alejandro Saucedo In this talk we will demystify the concept of “bias in machine learning“ through a hands-on example. We will be tasked to automate an end-to-end loan approval process by training a deep learning tensorflow model on sample data. We will then dissect the model and dataset showcasing hidden common risks, and we will provide important insight on the key tools and techniques you can use to identify and mitigate u