AI Explained Video Series: The AI Concepts You Need to Understand

Erika Renson

Published on September 3, 2020
Last Edited July 15, 2025

Table of Contents

  1. What are Shapley Values?
  2. What are Integrated Gradients?
  3. 5 Types of Explanation Methods
  4. Feature Importance
  5. Explainable ML Monitoring

As businesses recognize the need for enhanced digital capabilities and build out more robust and advanced Data Science teams, AI is one of the areas being most heavily invested in. It is viewed within many organizations as a potential panacea: How will I forecast demand, make business recommendations, or combat customer churn? AI. How will I detect fraud, make a lending decision, or optimize costs? AI. But before putting AI into production, there are many concepts that need to be understood to ensure your AI is transparent, accountable, ethical, and reliable.

In our AI Explained video series, we’re diving into some of these concepts in bite-sized videos to help you understand the meaning behind the hype:

1. What are Shapley Values?

The Shapley value is an attribution method from Cooperative Game Theory dating back to 1951. The basic concept is centered around how to fairly distribute surplus value across a coalition of all ‘players’ who contributed to the overall collective gain, assuming they all contributed at varying levels. The Shapley value was developed by Lloyd Shapley, who later won the Nobel Prize in Economics, and has been a popular tool in economics for decades.

Key Points:

  1. What does Shapley values have to do with explaining ML models?
    In data science, attribution allows you to attribute a model’s prediction on an input to features of the input. A key question in explaining predictions made by ML models is: “Why did the model make this prediction?”
  2. The marginal contribution challenge
    To compute Shapley values we need to measure the marginal contribution of a player, i.e., a feature. This means we need to know the model’s prediction when a certain feature is absent.
  3. The computation cost challenge
    There is a computation cost to going through all possible orderings. With n features there will be n! factorial orderings.

2. What are Integrated Gradients?

This video dives into another attribution method: Integrated Gradients. The Integrated Gradients method can be used to explain predictions made by deep neural networks (or any differentiable model). It is based on how to explain the relationship between a model's predictions and its features.

Key Points:

  1. How the method applies to deep neural networks.
  2. How more relevant attributions can be obtained by examining gradients across multiple counterfactual inputs.
  3. An overview of baselines.
    The baseline is meant to be an information-less input.

3. 5 Types of Explanation Methods

This video covers an overview of five types of explanation methods:

  1. Surrogate Model Based Explanations.
  2. Attribution Based Explanations.
  3. Contrastive Explanations.
  4. Counterfactual / Recourse Based Explanations.
  5. Example based explanations.

4. Feature Importance

In this video, we will discuss feature importance, a practice used to improve performance and understanding of models.

Key Techniques:

  1. Permutation Feature Importance.
  2. Leave-One-Out Retraining.
  3. Built-In Model-Specific Feature Importance Measures.

5. Explainable ML Monitoring

This video introduces Explainable ML Monitoring, which extends traditional monitoring to provide deep model insights with actionable steps.

Key Points:

  1. Why do we need explainable monitoring?
  2. What is explainable AI?
  3. What is the state of monitoring?
  4. What is an explainable monitoring solution?

If you have an idea for the topic for our next video, let us know. If you’d like to know when we add new topics to this series, subscribe here.