Introduction to Explainable Machine Learning

The content for this week includes description of FAIR and interpretable models, feature explainers and their (mis)utility, trust in ML, and other relevant concepts.

FAIR and FAIRness in Machine Learning

The content for this week includes description of bias in ML/AI applications, data bias, model bias, and making biomedical data FAIR and AI/ML ready.

Introduction to Explainable Machine Learning: Introduction | LIME | SHAP

Machine Learning Interpretability Toolkit

How to Stop Artificial Intelligence from Marginalizing Communities

How I'm Fighting Bias in Algorithms

Local Surrogate (LIME)

SHAP (SHapley Additive exPlanations)

Model Interpretability

Papers with Code - LIME Explained

Papers with Code - SHAP Explained

Simmons et al.: 'Responsible use of open-access developmental data: The Adolescent Brain Cognitive Development (ABCD) Study'

Katz et al.: 'Working towards understanding the role of FAIR for machine learning'

AI/ML Week 5 Data Exercise

AI/ML Week 5 Solutions