Data Skeptic

By Kyle Polich

What's Data Skeptic about?

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.

4.5

408 ratings

Download our free app to listen on your phone

LAST EPISODE

Serverless NLP Model Training

12.10.2019

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.

Data Skeptic episodes:

12.10.2019 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.
12.03.2019 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.
12.01.2019 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.
11.27.2019 ML Ops Kyle met up with Damian Brady at MS Ignite 2019 to discuss machine learning operations.
11.23.2019 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 ...
11.20.2019 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 ...
11.13.2019 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.
10.31.2019 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 ...
10.23.2019 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.
10.14.2019 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.
10.08.2019 SpanBERT Omer Levy joins us to discuss "SpanBERT: Improving Pre-training by Representing and Predicting Spans". https://arxiv.org/abs/1907.10529
09.23.2019 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.
09.16.2019 BERT is Magic Kyle pontificates on how impressed he is with BERT.
09.06.2019 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.
08.19.2019 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 ...
07.29.2019 BERT Kyle provides a non-technical overview of why Bidirectional Encoder Representations from Transformers (BERT) is a powerful tool for natural language processing projects.
07.22.2019 Onnx Kyle interviews Prasanth Pulavarthi about the Onnx format for deep neural networks.
07.15.2019 Catastrophic Forgetting Kyle and Linhda discuss some high level theory of mind and overview the concept machine learning concept of catastrophic forgetting.
07.08.2019 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.
06.21.2019 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 ...
06.15.2019 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 ...
06.08.2019 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 ...
06.01.2019 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.
05.25.2019 Neural Turing Machines Kyle and Linh Da discuss the concepts behind the neural Turing machine.
05.18.2019 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.
05.11.2019 NCAA Predictions on Spark In this episode, Kyle interviews Laura Edell at MS Build 2019. The conversation covers a number of topics, notably her NCAA Final 4 prediction model.
05.03.2019 The Transformer Kyle and Linhda discuss attention and the transformer - an encoder/decoder architecture that extends the basic ideas of vector embeddings like word2vec into a more contextual use case.
04.26.2019 Mapping Dialects with Twitter Data When users on Twitter post with geographic tags, it creates the opportunity for a variety of interesting questions to be posed having to do with language, dialects, and location. In this episode, Kyle interviews Bruno Gonçalves about his work studying ...
04.20.2019 Sentiment Analysis This is an interview with Ellen Loeshelle, Director of Product Management at Clarabridge. We primarily discuss sentiment analysis.
04.13.2019 Attention Primer A gentle introduction to the very high-level idea of "attention" in machine learning, as it will play a major role in some upcoming episodes over the next few weeks.
04.05.2019 Cross-lingual Short-text Matching Modern messaging technology has facilitated a trend towards highly compact, short messages send by users who can presume a great amount of context held between the communicating parties. The rules of grammar may be discarded and often visible errors are ...
03.29.2019 ELMo ELMo (Embeddings from Language Models) introduced the idea of deep contextualized word representations. It extends previous ideas like word2vec and GloVe. The ELMo model is a neural network able to map natural language into a vector space. This vector space, ...
03.23.2019 BLEU Bilingual evaluation understudy (or BLEU) is a metric for evaluating the quality of machine translation using human translation as examples of acceptable quality results. This metric has become a widely used standard in the research literature. But is it the ...
03.15.2019 Simultaneous Translation at Baidu While at NeurIPS 2018, Kyle chatted with Liang Huang about his work with Baidu research on simultaneous translation, which was demoed at the conference.
03.08.2019 Human vs Machine Transcription Machine transcription (the process of translating audio recordings of language to text) has come a long way in recent years. But how do the errors made during machine transcription compare to the errors made by a human transcriber? Find out ...
03.01.2019 seq2seq A sequence to sequence (or seq2seq) model is neural architecture used for translation (and other tasks) which consists of an encoder and a decoder. The encoder/decoder architecture has obvious promise for machine translation, and has been successfully applied this way. ...
02.22.2019 Text Mining in R Kyle interviews Julia Silge about her path into data science, her book Text Mining with R, and some of the ways in which she's used natural language processing in projects both personal and professional. Related Links https://stack-survey-2018.glitch.me/ https://stackoverflow.blog/2017/03/28/realistic-developer-fiction/
02.15.2019 Recurrent Relational Networks One of the most challenging NLP tasks is natural language understanding and reasoning. How can we construct algorithms that are able to achieve human level understanding of text and be able to answer general questions about it? This is truly ...
02.08.2019 Text World and Word Embedding Lower Bounds In the first half of this episode, Kyle speaks with Marc-Alexandre Côté and Wendy Tay about Text World. Text World is an engine that simulates text adventure games. Developers are encouraged to try out their reinforcement learning skills building agents ...
02.01.2019 word2vec Word2vec is an unsupervised machine learning model which is able to capture semantic information from the text it is trained on. The model is based on neural networks. Several large organizations like Google and Facebook have trained word embeddings (the ...
01.25.2019 Authorship Attribution In a recent paper, Leveraging Discourse Information Effectively for Authorship Attribution, authors Su Wang, Elisa Ferracane, and Raymond J. Mooney describe a deep learning methodology for predict which of a collection of authors was the author of a given document.
01.18.2019 Very Large Corpora and Zipf's Law The earliest efforts to apply machine learning to natural language tended to convert every token (every word, more or less) into a unique feature. While techniques like stemming may have cut the number of unique tokens down, researchers always had ...
01.11.2019 Semantic search at Github Github is many things besides source control. It's a social network, even though not everyone realizes it. It's a vast repository of code. It's a ticketing and project management system. And of course, it has search as well. In this ...
01.04.2019 Let's Talk About Natural Language Processing This episode reboots our podcast with the theme of Natural Language Processing for the next few months. We begin with introductions of Yoshi and Linh Da and then get into a broad discussion about natural language processing: what it is, ...
12.28.2018 Data Science Hiring Processes Kyle shares a few thoughts on mistakes observed by job applicants and also shares a few procedural insights listeners at early stages in their careers might find value in.
12.25.2018 Holiday Reading - Epicac Epicac by Kurt Vonnegut.
12.21.2018 Drug Discovery with Machine Learning In today's episode, Kyle chats with Alexander Zhebrak, CTO of Insilico Medicine, Inc. Insilico self describes as artificial intelligence for drug discovery, biomarker development, and aging research. The conversation in this episode explores the ways in which machine learning, in ...
12.14.2018 Sign Language Recognition At the NeurIPS 2018 conference, Stradigi AI premiered a training game which helps players learn American Sign Language. This episode brings the first of many interviews conducted at NeurIPS 2018. In this episode, Kyle interviews Chief Data Scientist Carolina Bessega ...
12.07.2018 Data Ethics This week, Kyle interviews Scott Nestler on the topic of Data Ethics. Today, no ubiquitous, formal ethical protocol exists for data science, although some have been proposed. One example is the INFORMS Ethics Guidelines. Guidelines like this are rather informal ...
11.30.2018 Escaping the Rabbit Hole Kyle interviews Mick West, author of Escaping the Rabbit Hole: How to Debunk Conspiracy Theories Using Facts, Logic, and Respect about the nature of conspiracy theories, the people that believe them, and how to help people escape the belief in ...

Older episodes

Data Skeptic

What's Data Skeptic about?

Download our free app to listen on your phone

Data Skeptic episodes:

Serverless NLP Model Training

Team Data Science Process

Ancient Text Restoration

ML Ops

Annotator Bias

NLP for Developers

Indigenous American Language Research

Talking to GPT-2

Reproducing Deep Learning Models

What BERT is Not

SpanBERT

BERT is Shallow

BERT is Magic

Applied Data Science in Industry

Building the howto100m Video Corpus

BERT

Onnx

Catastrophic Forgetting

Transfer Learning

Facebook Bargaining Bots Invented a Language

Under Resourced Languages

Named Entity Recognition

The Death of a Language

Neural Turing Machines

Data Infrastructure in the Cloud

NCAA Predictions on Spark

The Transformer

Mapping Dialects with Twitter Data

Sentiment Analysis

Attention Primer

Cross-lingual Short-text Matching

ELMo

BLEU

Simultaneous Translation at Baidu

Human vs Machine Transcription

seq2seq

Text Mining in R

Recurrent Relational Networks

Text World and Word Embedding Lower Bounds

word2vec

Authorship Attribution

Very Large Corpora and Zipf's Law

Semantic search at Github

Let's Talk About Natural Language Processing

Data Science Hiring Processes

Holiday Reading - Epicac

Drug Discovery with Machine Learning

Sign Language Recognition

Data Ethics

Escaping the Rabbit Hole

Other shows like Data Skeptic: