A Q&A about about the benefits of simplicity and the philosophical differences between statisticians and computer scientists.
In this Q&A on Explainable AI, Andrea Brennen speaks with Lab41 data scientist Nina Lopatina. Nina discusses different approaches to interpreting machine learning systems and points readers to several helpful open source tools and resources.
Dataviz.cafe is a public resource curated by IQT Labs for anyone interested in open-source software for data visualization. With over 700 software packages — summarized and tagged by data type, programming language, and other keywords — dataviz.cafe is designed to help people find free visualization tools for a wide variety of use-cases.
In this Q&A on Explainable AI, Andrea Brennen speaks with In-Q-Tel’s Peter Bronez about descriptive vs. prescriptive models, “white box” vs. “black box” explanation techniques, and why some models are easier to explain than others.
IQT Labs hosted our first “Join the Conversation” event on explainable AI in Washington DC on September 18. I kicked off the event with a talk summarizing 10 things I’ve learned about explainable AI. This post is based on that talk.
We need to design data products — artifacts and interfaces — that make data more accessible to less technical audiences. Good design gives us products that are accessible, informative and useful; even better design gives us experiences that are intuitive, compelling, and a pleasure to use.