Algorithmic Fairness
This episode includes an interview with Aaron Roth author of The Ethical Algorithm .
Jan 14, 2020•42 min
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.
Episodes
Interpretability
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 –...
Jan 07, 2020•33 min
NLP in 2019
A year in recap.
Dec 31, 2019•39 min
The Limits of NLP
We are joined by Colin Raffel to discuss the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer".
Dec 24, 2019•30 min
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.
Dec 15, 2019•21 min
Serverless NLP Model Training
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.
Dec 10, 2019•29 min
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.
Dec 03, 2019•41 min
Ancient Text Restoration
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.
Dec 01, 2019•41 min
ML Ops
Kyle met up with Damian Brady at MS Ignite 2019 to discuss machine learning operations.
Nov 27, 2019•37 min
Annotator Bias
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 tran...
Nov 23, 2019•26 min
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 advanced data scientists can focus more time on the bigger picture problems.
Nov 20, 2019•29 min
Indigenous American Language Research
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.
Nov 13, 2019•23 min
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 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....
Oct 31, 2019•29 min
Reproducing Deep Learning Models
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.
Oct 23, 2019•23 min
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.
Oct 14, 2019•27 min
SpanBERT
Omer Levy joins us to discuss "SpanBERT: Improving Pre-training by Representing and Predicting Spans". https://arxiv.org/abs/1907.10529
Oct 08, 2019•25 min
BERT is Shallow
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.
Sep 23, 2019•20 min
BERT is Magic
Kyle pontificates on how impressed he is with BERT.
Sep 16, 2019•18 min
Applied Data Science in Industry
Kyle sits down with Jen Stirrup to inquire about her experiences helping companies deploy data science solutions in a variety of different settings.
Sep 06, 2019•22 min
Building the howto100m Video Corpus
Video annotation is an expensive and time-consuming process. As a consequence, the available video datasets are useful but small. The availability of machine transcribed explainer videos offers a unique opportunity to rapidly develop a useful, if dirty, corpus of videos that are "self annotating", as hosts explain the actions they are taking on the screen. This episode is a discussion of the HowTo100m dataset - a project which has assembled a video corpus of 136M video clips with captions coveri...
Aug 19, 2019•23 min
BERT
Kyle provides a non-technical overview of why Bidirectional Encoder Representations from Transformers (BERT) is a powerful tool for natural language processing projects.
Jul 29, 2019•14 min
Onnx
Kyle interviews Prasanth Pulavarthi about the Onnx format for deep neural networks.
Jul 22, 2019•21 min
Catastrophic Forgetting
Kyle and Linhda discuss some high level theory of mind and overview the concept machine learning concept of catastrophic forgetting.
Jul 15, 2019•21 min
Transfer Learning
Sebastian Ruder is a research scientist at DeepMind. In this episode, he joins us to discuss the state of the art in transfer learning and his contributions to it.
Jul 08, 2019•30 min
Facebook Bargaining Bots Invented a Language
In 2017, Facebook published a paper called Deal or No Deal? End-to-End Learning for Negotiation Dialogues . In this research, the reinforcement learning agents developed a mechanism of communication (which could be called a language) that made them able to optimize their scores in the negotiation game. Many media sources reported this as if it were a first step towards Skynet taking over. In this episode, Kyle discusses bargaining agents and the actual results of this research....
Jun 21, 2019•23 min
Under Resourced Languages
Priyanka Biswas joins us in this episode to discuss natural language processing for languages that do not have as many resources as those that are more commonly studied such as English. Successful NLP projects benefit from the availability of like large corpora, well-annotated corpora, software libraries, and pre-trained models. For languages that researchers have not paid as much attention to, these tools are not always available.
Jun 15, 2019•17 min
Named Entity Recognition
Kyle and Linh Da discuss the class of approaches called "Named Entity Recognition" or NER. NER algorithms take any string as input and return a list of "entities" - specific facts and agents in the text along with a classification of the type (e.g. person, date, place).
Jun 08, 2019•17 min
The Death of a Language
USC students from the CAIS++ student organization have created a variety of novel projects under the mission statement of "artificial intelligence for social good". In this episode, Kyle interviews Zane and Leena about the Endangered Languages Project .
Jun 01, 2019•20 min
Neural Turing Machines
Kyle and Linh Da discuss the concepts behind the neural Turing machine.
May 25, 2019•25 min
Data Infrastructure in the Cloud
Kyle chats with Rohan Kumar about hyperscale, data at the edge, and a variety of other trends in data engineering in the cloud.
May 18, 2019•30 min