AI Academy

Developing Explainable AI (XAI)

Instructor: Brinnae Bent, PhD Duration: 8 hours to complete Recommended experience
Objective 1 Define key Explainable AI terminology and their relationships to each other
Objective 2 Describe commonly used interpretable and explainable approaches and their trade-offs
Objective 3 Evaluate considerations for developing XAI systems, including XAI evaluation approach, robustness, privacy, and integration with decision-making
Data Ethics
Artificial Intelligence and Machine Learning (AI/ML)
Applied Machine Learning
Machine Learning Methods
Artificial Intelligence
Generative AI
Artificial Neural Networks
Machine Learning
Information Privacy

Interpretable Machine Learning

Instructor: Brinnae Bent, PhD Duration: 1 week to complete at 10 hours a week
Objective 1 Describe and implement regression and generalized interpretable models
Objective 2 Demonstrate knowledge of decision trees, rules, and interpretable neural networks
Objective 3 Explain foundational Mechanistic Interpretability concepts, hypotheses, and experiments
Data Ethics
Natural language processing
Large Language Modeling
Predictive Modeling
Machine Learning
Deep Learning
Algorithms
Artificial Intelligence and Machine Learning (AI/ML)
Decision Tree Learning
Statistical Modeling
Applied Machine Learning
Python Programming
Regression Analysis
Artificial Neural Networks

Explainable Machine Learning (XAI)

Instructor: Brinnae Bent, PhD Duration: 1 week to complete at 10 hours a week
Objective 1 Explain and implement model-agnostic explainability methods.
Objective 2 Visualize and explain neural network models using SOTA techniques.
Objective 3 Describe emerging approaches to explainability in large language models (LLMs) and generative computer vision.
Generative AI
Large Language Modeling
Artificial Neural Networks
Image Analysis
Visualization (Computer Graphics)
Data Ethics
Predictive Analytics
Machine Learning
Artificial Intelligence and Machine Learning (AI/ML)
Deep Learning
Python Programming