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

18:01

BERT is Magic

Data Skeptic ·

2019/09/16

Kyle pontificates on how impressed he is with BERT.

en

21:51

Applied Data Science in Industry

Data Skeptic ·

2019/09/06

Kyle sits down with Jen Stirrup to inquire about her experiences helping companies deploy data science solutions in a variety of different settings.

en

22:38

Building the howto100m Video Corpus

Data Skeptic ·

2019/08/19

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 covering

en

13:44

BERT

Data Skeptic ·

2019/07/29

Kyle provides a non-technical overview of why Bidirectional Encoder Representations from Transformers (BERT) is a powerful tool for natural language processing projects.

en

20:32

Onnx

Data Skeptic ·

2019/07/22

Kyle interviews Prasanth Pulavarthi about the Onnx format for deep neural networks.

en

21:27

Catastrophic Forgetting

Data Skeptic ·

2019/07/15

Kyle and Linhda discuss some high level theory of mind and overview the concept machine learning concept of catastrophic forgetting.

en

29:51

Transfer Learning

Data Skeptic ·

2019/07/08

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.

en

23:08

Facebook Bargaining Bots Invented a Language

Data Skeptic ·

2019/06/21

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.

en

16:47

Under Resourced Languages

Data Skeptic ·

2019/06/15

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.

en

17:12

Named Entity Recognition

Data Skeptic ·

2019/06/08

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).

en

20:19

The Death of a Language

Data Skeptic ·

2019/06/01

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.

en

25:27

Neural Turing Machines

Data Skeptic ·

2019/05/25

Kyle and Linh Da discuss the concepts behind the neural Turing machine.

en

30:05

Data Infrastructure in the Cloud

Data Skeptic ·

2019/05/18

Kyle chats with Rohan Kumar about hyperscale, data at the edge, and a variety of other trends in data engineering in the cloud.

en

23:53

NCAA Predictions on Spark

Data Skeptic ·

2019/05/11

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.

en

15:23

The Transformer

Data Skeptic ·

2019/05/03

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.

en

25:20

Mapping Dialects with Twitter Data

Data Skeptic ·

2019/04/26

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 language in this way.

en

27:28

Sentiment Analysis

Data Skeptic ·

2019/04/20

This is an interview with Ellen Loeshelle, Director of Product Management at Clarabridge. We primarily discuss sentiment analysis.

en

14:51

Attention Primer

Data Skeptic ·

2019/04/13

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.

en

24:43

Cross-lingual Short-text Matching

Data Skeptic ·

2019/04/05

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 a normal part of the conversation. >>> Good mornink >>> morning Yet such short messages are also important for businesses whose users are unlikely to read a large block of text upon completing an order. Similarly, a business might want to offer

en

23:49

ELMo

Data Skeptic ·

2019/03/29

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, out of box, proved to be incredibly useful in a wide variety of seemingly unrelated NLP tasks like sentiment analysis and name entity recognition.

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