3.2 Methods

We have methods listed below to proceed. Below are the methods, that diverge under the Interpretable Machine Learning

• Machine Learning Models

• Model-Agnostic

• Sample Theory

Machine Learning Models - will be helping us with a specific algorithm to build the interpretable models and start working with it, in addition to it to help us explain the working

Model-Agnostic - Separating the explanations from the machine learning model (= model-agnostic interpretation methods) has some advantages, and we are going to discuss it in the coming sections.

Sample Theory - Is not related to the model interpretability, but a research sub-topic that would help us increase the computational speed to achieve our goal for interpretation and dealing with huge data to build the interpretable models. This is just a supporting method for our book, and should not be considered important for an Evaluation System.