Data Skeptic: Interpretability

Interpretability Practitioners

Sungsoo Ray Hong joins us to discuss the paper Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs. ... [more]

Facial Recognition Auditing

Deb Raji joins us to discuss her recent publication Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing. ... [more]

Robust Fit to Nature

Uri Hasson joins us this week to discuss the paper Robust-fit to Nature: An Evolutionary Perspective on Biological (and Artificial) Neural Networks. ... [more]

Black Boxes Are Not Required

Deep neural networks are undeniably effective. They rely on such a high number of parameters, that htey are appropriately described as “black boxes”. While black boxes lack desirably properties like interpretability and explainability, in some cases, their accuracy makes them incredibly useful. But does achiving “usefulness” require a black box? Can we be sure an equally valid but simpler solution does not exist? Cynthia Rudin helps us answer that question. We discuss her recent paper with co-author Joanna Radin titled (spoiler warning)… Why Are We Using Black Box Models in AI When We Don’t Need To? A Lesson From An Explainable AI Competition ... [more]

Robustness to Unforeseen Adversarial Attacks

Daniel Kang joins us to discuss the paper Testing Robustness Against Unforeseen Adversaries. ... [more]

Estimating the Size of Language Acquisition

Frank Mollica joins us to discuss the paper Humans store about 1.5 megabytes of information during language acquisition ... [more]

Interpretable AI in Healthcare

Jayaraman Thiagarajan joins us to discuss the recent paper Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models. ... [more]

Understanding Neural Networks

What does it mean to understand a neural network? That’s the question posted on this arXiv paper. Kyle speaks with Tim Lillicrap about this and several other big questions. ... [more]

Self-Explaining AI

Dan Elton joins us to discuss self-explaining AI. What could be better than an interpretable model? How about a model wich explains itself in a conversational way, engaging in a back and forth with the user. We discuss the paper Self-explaining AI as an alternative to interpretable AI which presents a framework for self-explainging AI. ... [more]

Plastic Bag Bans

Becca Taylor joins us to discuss her work studying the impact of plastic bag bans as published in Bag Leakage: The Effect of Disposable Carryout Bag Regulations on Unregulated Bags from the Journal of Environmental Economics and Management. How does one measure the impact of these bans? Are they achieving their intended goals? Join us and find out! ... [more]

Self Driving Cars and Pedestrians

We are joined by Arash Kalatian to discuss Decoding pedestrian and automated vehicle interactions using immersive virtual reality and interpretable deep learning. ... [more]

Computer Vision is Not Perfect

Computer Vision is not Perfect Julia Evans joins us help answer the question why do neural networks think a panda is a vulture. Kyle talks to Julia about her hands-on work fooling neural networks. Julia runs Wizard Zines which publishes works such as Your Linux Toolbox. You can find her on Twitter @b0rk ... [more]

Uncertainty Representations

Jessica Hullman joins us to share her expertise on data visualization and communication of data in the media. We discuss Jessica’s work on visualizing uncertainty, interviewing visualization designers on why they don't visualize uncertainty, and modeling interactions with visualizations as Bayesian updates. Homepage: Lab: MU Collective ... [more]

AlphaGo, COVID-19 Contact Tracing, and New Data Set

George led a discussion about AlphaGo - The Movie | Full Documentary. Lan informed us about the COVID-19 Open Research Dataset. Kyle shared some thoughts about the paper Beyond R_0: the importance of contact tracing when predicting epidemics. ... [more]

Visualizing Uncertainty

... [more]

Interpretability Tooling

Pramit Choudhary joins us to talk about the methodologies and tools used to assist with model interpretability. ... [more]

Shapley Values

Kyle and Linhda discuss how Shapley Values might be a good tool for determining what makes the cut for a home renovation. ... [more]

Anchors as Explanations

We welcome back Marco Tulio Ribeiro to discuss research he has done since our original discussion on LIME. In particular, we ask the question Are Red Roses Red? and discuss how Anchors provide high precision model-agnostic explanations. Please take our listener survey. ... [more]

Mathematical Models of Ecological Systems

... [more]

Adversarial Explanations

Walt Woods joins us to discuss his paper Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness with co-authors Jack Chen and Christof Teuscher. ... [more]


Andrei Barbu joins us to discuss ObjectNet - a new kind of vision dataset. In contrast to ImageNet, ObjectNet seeks to provide images that are more representative of the types of images an autonomous machine is likely to encounter in the real world. Collecting a dataset in this way required careful use of Mechanical Turk to get Turkers to provide a corpus of images that removes some of the bias found in ImageNet. ... [more]

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 More from Enrico with co-host Moritz Stefaner on the Data Stories podcast! ... [more]

Interpretable One Shot Learning

We welcome Su Wang back to Data Skeptic to discuss the paper Distributional modeling on a diet: One-shot word learning from text only. ... [more]

Fooling Computer Vision

Wiebe van Ranst joins us to talk about a project in which specially designed printed images can fool a computer vision system, preventing it from identifying a person.  Their attack targets the popular YOLO2 pre-trained image recognition model, and thus, is likely to be widely applicable. ... [more]

Algorithmic Fairness

This episode includes an interview with Aaron Roth author of The Ethical Algorithm. ... [more]


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 models actually work are becoming increasingly important to ask. Welcome to Data Skeptic Interpretability. In this episode, Kyle interviews Christoph Molnar about his book Interpretable Machine Learning. Thanks to our sponsor, the Gartner Data & Analytics Summit going on in Grapevine, TX on March 23 – 26, 2020. Use discount code: dataskeptic. Music Our new theme song is #5 by Big D and the Kids Table. Incidental music by Tanuki Suit Riot. ... [more]