🎨
Explainable-AI
  • Explainable AI
  • Preface
  • How to use this book?
  • Contents
  • What is Explainable AI?
  • Why do we need Explainablity?
  • Explainable systems and Black box systems
  • Types of Explainability Techniques
  • Explainable Models
    • Linear Regression
      • Assumptions
      • Model
      • Statistical Interpretation
    • Decision Trees
      • How Do They Work?
      • Creating the model
      • Interpretation
  • Explainability Techniques for Classical ML
    • SHAP (SHapley Additive exPlanations)
    • Surrogate model
    • LIME (Local Interpretable Model-Agnostic Explanations)
    • PDP (Partial Dependence Plot)
    • ICE (Individual Conditional Expectation Plots)
    • ALE (Accumulated Local Effects Plot)
  • Datasets
    • Medical Cost Personal Dataset
    • Telecom Churn Dataset
    • Sales Opportunity Size Dataset
    • Pima Indians Diabetes Dataset
  • Implementation of these techniques on different models
    • Logistic Regression - SHAP
    • Random Forest - LIME
    • GBM - PDP
    • GBM - ICE
    • Deep Learning - Surrogate
  • Future scope
  • Contributors
  • Citing this Book
Powered by GitBook
On this page

Was this helpful?

What is Explainable AI?

Explainability refers to the ability to explain the choice taken by the AI system. The rise of explainability is attributed to most AI systems being a complex and black box with no explanation for the actions.

Explainability leads to transparency, which means being upfront and visible about the action AI takes, which helps in evaluating the action taken by AI systems, whether these are consistent with the values widely accepted as societal ethics.

Explainability is part of Ethical AI, which deals with broader things like privacy, security, transparency, and others. Ethics in AI is a set of values, principles and techniques that employ widely accepted standards of right and wrong to guide moral conduct in the development and use of AI technologies.

AI and Machine Learning systems have access to tremendous amounts of data and computing power, they will only become more effective and more used as the age of information evolves. With this pace of development and progress, it may not be long before AI technologies become gatekeepers for the advancement of vital public interests and sustainable human development. This makes the Explainability in AI a crucial point of discussion and deliberation.

PreviousContentsNextWhy do we need Explainablity?

Last updated 3 years ago

Was this helpful?