Opening the black box – Part 1: Introduction to Model Explainability
Although Machine Learning has been around for quite a while, most people are only now beginning to become acquainted with the technology. Therefore, blindly trusting a prediction that came out of a black box model might still be quite daunting to most.
In this video, our data scientist Wout gives an introduction to Model Explainability which allows us to detect possible biases or preferences that might have sneaked into the Machine Learning algorithm.
As data scientists, we are on the frontline in the battle of safeguarding ethical practices within the field of Artificial Intelligence and Machine Learning. Model explanations provide us with the much-needed tool to check for potential biases before implementing newly trained algorithms.
Want to read more? Go to the full article.