Interpretability

As AI grows more powerful, understanding how models make decisions becomes critical. This season explores the tools and frameworks for interpreting machine learning — from visualizations and feature attributions to simpler, more transparent models. It also tackles fairness, accountability, and the human need to trust complex systems. Each episode highlights the push for clarity in a field often criticized for its opacity.

Episodes

• Interpretability Practitioners — Sungsoo Ray Hong joins us to discuss the paper Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs .
• Interpretable AI in Healthcare — Jayaraman Thiagarajan joins us to discuss the recent paper Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models .
• Interpretability Tooling — Pramit Choudhary joins us to talk about the methodologies and tools used to assist with model interpretability.
• Visualization and Interpretability — Enrico Bertini joins us to discuss how data visualization can be used to help make machine learning more interpretable and explainable. Find out more about Enrico at http://enrico.bertini.io/ . More f
• Interpretable One Shot Learning — We welcome [Su Wang](https://scholar.google.com/citations?hl=en&user=bJZV7r4AAAAJ) back to Data Skeptic to discuss the paper [Distributional modeling on a diet: One-shot word learning from text only](
• Interpretability — ## Interpretability Machine learning has shown a rapid expansion into every sector and industry. With increasing reliance on models and increasing stakes for the decisions of models, questions of how