Hands-on Introduction to Interpreting Machine Learning Models

Interpretable machine learning is needed because machine learning by itself is incomplete as a solution. The complex problems we solve with machine learning can’t be solved with traditional software development precisely because we don’t understand all of the problem space we’re trying to solve. By explaining a model’s decisions, we can cover gaps in our understanding of the problem, and increase trust in the products we build with AI. In this session, we will cover the importance of model interpretation and explain various methods and their classifications, including feature importance, feature summary, and local explanations.