Explanation to ML models

AI algorithms often operate as "black boxes" that take input and provide output with no way to understand their inner workings. The goal of explainable AI is to make the rationale behind the output of an algorithm understandable by humans. I will talk about how machine learning model results can be interpreted and explained. The discussion will be around methods used for explanation e.g. SHAP values etc. and how to interpret them. This will cover the working of the model explanations along with a short demo.