Udemybeginneren

Explainable Al (XAI) with Python

Learn Explainable AI (XAI) easily! Understand how AI makes decisions. Simple methods for transparency & trust in machine learning.

3.8(365)
3,632students
7h 53m
Certificate
Parteek Bhatia
Parteek BhatiaProfessor, CSED, TIET, Patiala, India

Course Content

Explainable Al (XAI) with Python is a beginner-level Udemy course taught by Parteek Bhatia. It runs 7h 53m, is taught in English, and includes a certificate of completion. Learners rate it 3.8 out of 5 from 365 reviews, with 3,632 students enrolled. It is a paid course, last updated July 2022.

Unlock the secrets of your AI models with Explainable AI (XAI) using Python! This comprehensive course dives deep into the rapidly evolving field of Explainable Artificial Intelligence, empowering you to understand why AI makes the decisions it does. As AI becomes increasingly integrated into critical applications, understanding and justifying AI decisions is no longer optional – it's essential, especially with emerging regulations.

What you'll learn:

  • Core XAI Techniques: Master powerful methods for making your AI models more transparent and trustworthy.
  • LIME (Local Interpretable Model-Agnostic Explanations): Explore the working principles and mathematical modeling of LIME to gain insights into individual predictions. Learn how to generate local explanations for any machine learning model.
  • SHAP (SHapley Additive exPlanations): Discover SHAP values and their application in generating both local and global explanations, providing a unified measure of feature importance.
  • Counterfactual Explanations: Understand the concept of "what if" scenarios and learn how to generate actionable counterfactuals using techniques like Diverse Counterfactual Explanations (DiCE). DiCE helps identify the minimal changes needed to achieve a desired outcome.
  • AI Fairness: Delve into the crucial aspect of AI fairness and how to leverage XAI to identify and mitigate bias in your models.
  • Visual Explanations with Google's What-If Tool (WIT): Utilize Google's WIT to create intuitive visual explanations for your AI models, making them easier to understand and debug.
  • LRP (Layer-wise Relevance Propagation): Learn how LRP works to generate explanations specifically for neural networks, revealing which input features contribute most to the model's output.

Hands-on Learning:

This course emphasizes practical application. Through engaging hands-on sessions, you'll learn to implement XAI techniques using Python. We provide datasets and code for you to practice and apply these techniques to your own AI models. Real-world case studies highlight the importance of explainable AI in diverse domains.

By the end of this course, you'll be equipped to:

  • Visualize and interpret AI model behavior.
  • Explain complex AI decisions to stakeholders.
  • Build trustworthy and transparent AI systems.
  • Comply with evolving AI regulations.
$ whoami — the devs behind tutorialsearch.io

Want AI in your product? Hire the team behind TutorialSearch.io

LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.

5.0(33)
1h 50m
all
skillshare
5.0(766)
2h 58m
intermediate
skillshare
skillshare