x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

Data Skeptic

The Data Skeptic Podcast features interviews and discussion of topics related to data science, statistics, machine learning, artificial intelligence and the like, all from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.

technology mathematics

All Episodes

35:49

Visualization and Interpretability

Data Skeptic ·

2020/01/31

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!

en

30:40

Interpretable One Shot Learning

Data Skeptic ·

2020/01/26

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

en

25:26

Fooling Computer Vision

Data Skeptic ·

2020/01/22

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.

en

42:10

Algorithmic Fairness

Data Skeptic ·

2020/01/14

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

en

32:43

Interpretability

Data Skeptic ·

2020/01/07

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,

en

38:43

NLP in 2019

Data Skeptic ·

2019/12/31

A year in recap.

en

29:47

The Limits of NLP

Data Skeptic ·

2019/12/24

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

en

20:34

Jumpstart Your ML Project

Data Skeptic ·

2019/12/15

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

en

29:02

Serverless NLP Model Training

Data Skeptic ·

2019/12/10

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.

en

41:24

Team Data Science Process

Data Skeptic ·

2019/12/03

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.

en

41:13

Ancient Text Restoration

Data Skeptic ·

2019/12/01

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.

en

36:31

ML Ops

Data Skeptic ·

2019/11/27

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

en

25:55

Annotator Bias

Data Skeptic ·

2019/11/23

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 these advancements, an NLP researcher might get value out of fewer examples since they can use the

en

29:01

NLP for Developers

Data Skeptic ·

2019/11/20

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.

en

22:51

Indigenous American Language Research

Data Skeptic ·

2019/11/13

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.

en

29:10

Talking to GPT-2

Data Skeptic ·

2019/10/31

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-2. We discuss his experiences as well as some novel thoughts on artificial intelligence.

en

22:43

Reproducing Deep Learning Models

Data Skeptic ·

2019/10/23

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.

en

27:00

What BERT is Not

Data Skeptic ·

2019/10/14

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.

en

24:49

SpanBERT

Data Skeptic ·

2019/10/08

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

en

20:29

BERT is Shallow

Data Skeptic ·

2019/09/23

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.

en

599 results

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs