Introduction to Interpretable Machine Learning - Cynthia Rudin

Explore the fundamentals of interpretable machine learning in this 57-minute lecture from the 2022 Program for Women and Mathematics. Delve into key concepts such as vectors, classification, and natural language processing as Duke University's Cynthia Rudin presents the Terng Lecture. Gain insights into model complexity, decision trees, and information theory while examining practical demonstrations and real-world data sets. Discover how these principles contribute to creating transparent and understandable machine learning models, essential for various applications in today's data-driven world.

Introduction
Machine Learning
Vectors
Classification
Demonstration
Natural Language Processing
Model Complexity
Decision Trees
Data Set
Information Theory