1,783
  • Catastrophic Forgetting - Duration: 21 minutes.

    • 2 days ago
    • 30 views
    Kyle and Linhda discuss some high level theory of mind and overview the concept machine learning concept of catastrophic forgetting.
  • Facebook Bargaining Bots Invented a Language - Duration: 23 minutes.

    • 3 weeks ago
    • 57 views
    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...
  • Gamazda - Channel

    • 9 videos
    Кавер на пианино, рояле, фортепиано :)
    Piano cover from Russia
    • CHANNEL
    86,395
  • Under Resourced Languages - Duration: 16 minutes.

    • 1 month ago
    • 35 views
    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...
  • Dogman Encounters - Channel

    • 264 videos
    Thanks for visiting the Dogman Encounters Radio YouTube Channel!

    I’m Vic Cundiff; creator and host of Dogman Encounters. Tune in every Friday, to hear me talk with real eyewitnesses, about their t
    • CHANNEL
    49,730
  • Named Entity Recognition - Duration: 17 minutes.

    • 1 month ago
    • 51 views
    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 th...
  • The Death of a Language - Duration: 20 minutes.

    • 1 month ago
    • 77 views
    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...
  • Neural Turing Machines - Duration: 25 minutes.

    • 1 month ago
    • 111 views
    Kyle and Linh Da discuss the concepts behind the neural Turing machine.
  • Data Infrastructure in the Cloud - Duration: 30 minutes.

    • 1 month ago
    • 53 views
    Kyle chats with Rohan Kumar about hyperscale, data at the edge, and a variety of other trends in data engineering in the cloud.
  • NCAA Predictions on Spark - Duration: 23 minutes.

    • 2 months ago
    • 44 views
    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.
  • The Transformer - Duration: 15 minutes.

    • 2 months ago
    • 61 views
    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.
  • Mapping Dialects with Twitter Data - Duration: 25 minutes.

    • 2 months ago
    • 87 views
    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, ...
  • Sentiment Analysis - Duration: 27 minutes.

    • 2 months ago
    • 81 views
    This is an interview with Ellen Loeshelle, Director of Product Management at Clarabridge. We primarily discuss sentiment analysis.
  • Attention Primer - Duration: 14 minutes.

    • 3 months ago
    • 61 views
    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.
  • Ska Tune Network - Channel

    • 134 videos
    I make ska covers of songs
    • CHANNEL
    77,419
  • Cross-lingual Short-text Matching - Duration: 24 minutes.

    • 3 months ago
    • 44 views
    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...
  • ELMo - Duration: 23 minutes.

    • 3 months ago
    • 130 views
    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...
  • BLEU - Duration: 42 minutes.

    • 3 months ago
    • 92 views
    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 w...
  • Simultaneous Translation at Baidu - Duration: 24 minutes.

    • 4 months ago
    • 42 views
    While at NeurIPS 2018, Kyle chatted with Liang Huang about his work with Baidu research on simultaneous translation, which was demoed at the conference.
  • Human vs Machine Transcription - Duration: 32 minutes.

    • 4 months ago
    • 58 views
    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 e...
  • seq2seq - Duration: 21 minutes.

    • 4 months ago
    • 95 views
    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 ...
  • Text Mining in R - Duration: 20 minutes.

    • 4 months ago
    • 76 views
    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 profess...
  • Recurrent Relational Networks - Duration: 19 minutes.

    • 5 months ago
    • 86 views
    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 answ...
  • Text World and Word Embedding Lower Bounds - Duration: 39 minutes.

    • 5 months ago
    • 50 views
    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 t...
  • word2vec - Duration: 31 minutes.

    • 5 months ago
    • 121 views
    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 l...
  • Authorship Attribution - Duration: 50 minutes.

    • 5 months ago
    • 80 views
    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 ...
  • Very Large Corpora and Zipf's Law - Duration: 24 minutes.

    • 5 months ago
    • 112 views
    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 nu...
  • Semantic search at Github - Duration: 34 minutes.

    • 6 months ago
    • 293 views
    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 cou...
  • Let's Talk About Natural Language Processing - Duration: 37 minutes.

    • 6 months ago
    • 153 views
    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 abo...
  • Data Science Hiring Processes - Duration: 33 minutes.

    • 6 months ago
    • 253 views
    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.
  • Holiday Reading - Epicac - Duration: 21 minutes.

    • 6 months ago
    • 41 views
    Epicac by Kurt Vonnegut.
  • Drug Discovery with Machine Learning - Duration: 29 minutes.

    • 6 months ago
    • 340 views
    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 res...
  • Sign Language Recognition - Duration: 19 minutes.

    • 7 months ago
    • 211 views
    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 201...
  • Data Ethics - Duration: 19 minutes.

    • 7 months ago
    • 69 views
    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...
  • Escaping the Rabbit Hole - Duration: 33 minutes.

    • 7 months ago
    • 132 views
    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 the...
  • Theorem Provers - Duration: 19 minutes.

    • 7 months ago
    • 68 views
    Fake news attempts to lead readers/listeners/viewers to conclusions that are not descriptions of reality.  They do this most often by presenting false premises, but sometimes by presenting fla...
  • Automated Fact Checking - Duration: 31 minutes.

    • 8 months ago
    • 120 views
    Fake news can be responded to with fact-checking. However, it's easier to create fake news than the fact check it.

    Full Fact is the UK's independent fact-checking organization. In this epi...
  • Single Source of Truth - Duration: 29 minutes.

    • 8 months ago
    • 71 views
    In mathematics, truth is universal.  In data, truth lies in the where clause of the query.

    As large organizations have grown to rely on their data more significantly for decision making, a...
  • Detecting Fast Radio Bursts with Deep Learning - Duration: 44 minutes.

    • 8 months ago
    • 45 views
    Fast radio bursts are an astrophysical phenomenon first observed in 2007. While many observations have been made, science has yet to explain the mechanism for these events. This has led some to ask...
  • Being Bayesian - Duration: 24 minutes.

    • 8 months ago
    • 106 views
    This episode explores the root concept of what it is to be Bayesian: describing knowledge of a system probabilistically, having an appropriate prior probability, know how to weigh new evidence, and...
  • Modeling Fake News - Duration: 33 minutes.

    • 8 months ago
    • 84 views
    This is our interview with Dorje Brody about his recent paper with David Meier, How to model fake news. This paper uses the tools of communication theory and a sub-topic called filtering theory to ...
  • louvain - Duration: 26 minutes.

    • 9 months ago
    • 278 views
    Without getting into definitions, we have an intuitive sense of what a "community" is. The Louvain Method for Community Detection is one of the best known mathematical techniques designed to detect...
  • Cultural Cognition of Scientific Consensus - Duration: 31 minutes.

    • 9 months ago
    • 86 views
    In this episode, our guest is Dan Kahan about his research into how people consume and interpret science news.

    In an era of fake news, motivated reasoning, and alternative facts, important ques...
  • False Discovery Rates - Duration: 25 minutes.

    • 9 months ago
    • 133 views
    A false discovery rate (FDR) is a methodology that can be useful when struggling with the problem of multiple comparisons.

    In any experiment, if the experimenter checks more than one dependent ...
  • Deep Fakes - Duration: 30 minutes.

    • 9 months ago
    • 100 views
    Digital videos can be described as sequences of still images and associated audio. Audio is easy to fake. What about video?

    A video can easily be broken down into a sequence of still images rep...
  • Fake News Midterm - Duration: 19 minutes.

    • 10 months ago
    • 44 views
    In this episode, Kyle reviews what we've learned so far in our series on Fake News and talks briefly about where we're going next.
  • Quality Score - Duration: 18 minutes.

    • 10 months ago
    • 48 views
    Two weeks ago we discussed click through rates or CTRs and their usefulness and limits as a metric. Today, we discuss a related metric known as quality score.

    While that phrase has pr...
  • The Knowledge Illusion - Duration: 40 minutes.

    • 10 months ago
    • 155 views
    Kyle interviews Steven Sloman, Professor in the school of Cognitive, Linguistic, and Psychological Sciences at Brown University. Steven is co-author of The Knowledge Illusion: Why We Never Think Al...
  • Click Through Rates - Duration: 31 minutes.

    • 10 months ago
    • 61 views
    A Click Through Rate (CTR) is the proportion of clicks to impressions of some item of content shared online. This terminology is most commonly used in digital advertising but applies just as well t...
  • Algorithmic Detection of Fake News - Duration: 46 minutes.

    • 11 months ago
    • 428 views
    The scale and frequency with which information can be distributed on social media makes the problem of fake news a rapidly metastasizing issue. To do any content filtering or labeling demands an al...
to add this to Watch Later

Add to

Loading playlists...