Interpretable Machine Learning

Instructor: Brinnae Bent, PhD

Intermediate Level • 1 week to complete at 10 hours a week • Flexible Schedule

What You'll Learn

  • Describe and implement regression and generalized interpretable models
  • Demonstrate knowledge of decision trees, rules, and interpretable neural networks
  • Explain foundational Mechanistic Interpretability concepts, hypotheses, and experiments

Skills You'll Gain

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

Shareable Certificate

Earn a shareable certificate to add to your LinkedIn profile

Outcomes

  • Learn new concepts from industry experts
  • Gain a foundational understanding of a subject or tool
  • Develop job-relevant skills with hands-on projects
  • Earn a shareable career certificate

There are 3 modules in this course

In this module, you will be introduced to the concepts of regression and generalized models for interpretability. You will learn how to describe interpretable machine learning and differentiate between interpretability and explainability, explain and implement regression models in Python, and demonstrate knowledge of generalized models in Python. You will apply these learnings through discussions, guided programming labs, and a quiz assessment.

In this module, you will be introduced to the concepts of decision trees, decision rules, and interpretability in neural networks. You will learn how to explain and implement decision trees and decision rules in Python and define and explain neural network interpretable model approaches, including prototype-based networks, monotonic networks, and Kolmogorov-Arnold networks. You will apply these learnings through discussions, guided programming labs, and a quiz assessment.

In this module, you will be introduced to the concept of Mechanistic Interpretability. You will learn how to explain foundational Mechanistic Interpretability concepts, including features and circuits; describe the Superposition Hypothesis; and define Representation Learning to be able to analyze current research on scaling Representation Learning to LLMs. You will apply these learnings through discussions, guided programming labs, and a quiz assessment.