Data Skeptic

The Spread of Misinformation Online

Neil Johnson joins us to discuss the paper The online competition between pro- and anti-vaccination views.

Voting Mechanisms

Steven Heilman joins us to discuss his paper Designing Stable Elections. For a general interest article, see: https://theconversation.com/the-electoral-college-is-surprisingly-vulnerable-to-popular-vote-changes-141104 Steven Heilman receives funding from the National Science Foundation. Any opinions, findings, and conclusions or recommendations expressed in this material are those ...

Fraud Detection in Real Time

In this solo episode, Kyle overviews the field of fraud detection with eCommerce as a use case. He discusses some of the techniques and system architectures used by companies to fight fraud with a focus on why these things need ...

Human Computer Interaction and Online Privacy

Moses Namara from the HATLab joins us to discuss his research into the interaction between privacy and human-computer interaction.

GANs Can Be Interpretable

Erik Härkönen joins us to discuss the paper GANSpace: Discovering Interpretable GAN Controls. During the interview, Kyle makes reference to this amazing interpretable GAN controls video and it’s accompanying codebase found here. Erik mentions the GANspace collab notebook which is ...

Interpretability Practitioners

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

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.

Robustness to Unforeseen Adversarial Attacks

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

Interpretable AI in Healthcare

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

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 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.

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 ...

Visualizing Uncertainty

Shapley Values

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

Mathematical Models of Ecological Systems

ObjectNet

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 ...

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.

Algorithmic Fairness

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

NLP in 2019

A year in recap.

Jumpstart Your ML Project

Seth Juarez joins us to discuss the toolbox of options available to a data scientist to jumpstart or extend their machine learning efforts.

Team Data Science Process

Buck Woody joins Kyle to share experiences from the field and the application of the Team Data Science Process - a popular six-phase workflow for doing data science.

ML Ops

Kyle met up with Damian Brady at MS Ignite 2019 to discuss machine learning operations.

NLP for Developers

While at MS Build 2019, Kyle sat down with Lance Olson from the Applied AI team about how tools like cognitive services and cognitive search enable non-data scientists to access relatively advanced NLP tools out of box, and how more ...

Talking to GPT-2

GPT-2 is yet another in a succession of models like ELMo and BERT which adopt a similar deep learning architecture and train an unsupervised model on a massive text corpus. As we have been covering recently, these approaches are showing ...

What BERT is Not

Allyson Ettinger joins us to discuss her work in computational linguistics, specifically in exploring some of the ways in which the popular natural language processing approach BERT has limitations.