Online Course – Google’s Certified Professional Internship in Explainable AI (XAI), Duke University

Build ethical and transparent AI systems. Gain skills in ethical AI explanation and open source techniques to create trusted and transparent machine learning solutions.

Suggested by: Coursera (What is Coursera?)

Start your Coursera.com free trial today
קורס אונליין - התמחות מקצועית מוסמכת ב-Explainable AI (XAI) של גוגל

Professional Certificate

Beginners

No prior knowledge required

Time to complete the course

7-day free trial

No unnecessary risks

Skills you will acquire in the course

  • Developing transparent and reliable AI systems
  • Deep understanding of Explainable AI (XAI) concepts
  • Ability to apply interpretable machine learning
  • Using advanced explanation techniques for large language models (LLMs)
  • Working with generative computer imaging
  • An investigation of ethical considerations and biases in models
  • Performing Python lab activities with different models
  • Implementing local annotations using LIME, SHAP, and Anchors
  • Creating transparent and ethical AI solutions to real challenges

What you will learn in the course

Courses for which the course is suitable

  • AI professionals
  • Data scientists
  • Machine Learning Engineers
  • Product Managers
  • Artificial Intelligence Developers
  • Data scientists
  • Artificial Intelligence Ethics Experts
  • Data analysts
  • Artificial Intelligence Consultants
  • Project managers in the field of advanced technologies

Specialization in Explanatory Artificial Intelligence (XAI)

In an era where artificial intelligence (AI) is rapidly transforming sensitive areas such as healthcare, finance, and criminal justice, the ability to develop AI systems that are not only accurate but also transparent and trustworthy is critical. The specialization is designed to provide AI professionals, data scientists, machine learning engineers, and product managers with the knowledge and skills needed to create AI solutions that meet the highest standards of ethics and responsibility.

Course instructor

The courses are taught by Dr. Brina Bennett, an expert in bridging the gap between research and industry in machine learning.

Key issues

  • Explainable AI (XAI) concepts
  • Interpretable machine learning
  • Advanced Explanatory Techniques for Large Language Models (LLMs)
  • Generative computer imaging

Hands-on Learning Project

The internship offers practical projects that deepen the understanding of XAI and interpretable machine learning.

Projects in courses

  • Course 1: Exploration of ethical considerations and biases through moral machine reflections, research, and case studies.
  • Course 2: Python lab activities with Jupyter notebooks that focus on implementing models such as GLMs, GAMs, decision trees, and RuleFit.
  • Course 3: Advanced labs focusing on local explanations using LIME, SHAP, and Anchors.

The projects offered in this specialization prepare learners to create transparent and ethical AI solutions to real-world challenges.

Details of the courses that make up the specialization

Developing Explainable Intuition (XAI)

Course 1 – 8 hours

What you will learn:

  • Determine key terms of explainable intuition and the relationships between them.
  • Describe common, explainable, and reasonable approaches to trading.
  • Prepare considerations for developing XAI systems, including XAI evaluation methodology, robustness, privacy, and integration with decision-making

The skills you will gain:

  • XAI
  • Machine learning
  • Explainable Intuition (XAI)
  • Artificial Intelligence
  • Explainable machine learning

Course 2 – 13 hours

What you will learn:

  • Describe and apply regression models and general explanatory models
  • The model has knowledge of decision trees, rules, and explainable neural networks.
  • Explain basic concepts of mechanistic interpretability, hypotheses, and experiments

The skills you will gain:

  • Machine learning
  • Responsible AI
  • Artificial Intelligence
  • Mechanistic incompatibilities
  • Explainable machine learning

Course 3 – 14 hours

What you will learn:

  • Explain and apply model-independent information methods
  • Illustrating and explaining neural network models using SOTA techniques
  • Describe emerging approaches to explainability in large language models (LLMs) and generative computer vision

Related products