Data Skeptic

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 .

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.

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...

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 from Enrico with co-host Moritz Stefaner on the  Data Stories  podcast!

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

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.

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

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 Learni...

A year in recap.

We are joined by Colin Raffel to discuss the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer".

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

Alex Reeves joins us to discuss some of the challenges around building a serverless, scalable, generic machine learning pipeline.   The is a technical deep dive on architecting solutions and a discussion of some of the design choices made.

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.  

Thea Sommerschield joins us this week to discuss the development of Pythia - a machine learning model trained to assist in the reconstruction of ancient language text.

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

The modern deep learning approaches to natural language processing are voracious in their demands for large corpora to train on.  Folk wisdom estimates used to be around 100k documents were required for effective training.  The availability of broadly trained, general-purpose models like BERT has made it possible to do transfer learning to achieve novel results on much smaller corpora. Thanks to t...

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 advanced data scientists can focus more time on the bigger picture problems.

Manuel Mager joins us to discuss natural language processing for low and under-resourced languages.   We discuss current work in this area and the Naki Project which aggregates research on NLP for native and indigenous languages of the American continent.

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 tremendous promise, but how close are they to an AGI?  Our guest today, Vazgen Davidyants wondered exactly that, and have conversations with a Chatbot running GPT-...

Rajiv Shah attempted to reproduce an earthquake-predicting deep learning model.   His results exposed some issues with the model.   Kyle and Rajiv discuss the original paper and Rajiv's analysis.

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.

Omer Levy joins us to discuss "SpanBERT: Improving Pre-training by Representing and Predicting Spans". https://arxiv.org/abs/1907.10529

Tim Niven joins us this week to discuss his work exploring the limits of what BERT can do on certain natural language tasks such as adversarial attacks, compositional learning, and systematic learning.

Kyle pontificates on how impressed he is with BERT.