Deep Learning for NLP: From the Trenches with Charlene Chambliss - #433
Play • 46 min

Today we’re joined by Charlene Chambliss, Machine Learning Engineer at Primer AI. 

Charlene, who we also had the pleasure of hosting at NLP Office Hours during TWIMLfest, is back to share some of the work she’s been doing with NLP. In our conversation, we explore her experiences working with newer NLP models and tools like BERT and HuggingFace, as well as whats she’s learned along the way with word embeddings, labeling tasks, debugging, and more. We also focus on a few of her projects, like her popular multi-lingual BERT project, and a COVID-19 classifier. 

Finally, Charlene shares her experience getting into data science and machine learning coming from a non-technical background, and what the transition was like, and tips for people looking to make a similar shift.

Towards Data Science
Towards Data Science
The TDS team
66. Owain Evans - Predicting the future of AI
Most researchers agree we’ll eventually reach a point where our AI systems begin to exceed human performance at virtually every economically valuable task, including the ability to generalize from what they’ve learned to take on new tasks that they haven’t seen before. These artificial general intelligences (AGIs) would in all likelihood have transformative effects on our economies, our societies and even our species. No one knows what these effects will be, or when AGI systems will be developed that can bring them about. But that doesn’t mean these things aren’t worth predicting or estimating. The more we know about the amount of time we have to develop robust solutions to important AI ethics, safety and policy problems, the more clearly we can think about what problems should be receiving our time and attention today. That’s the thesis that motivates a lot of work on AI forecasting: the attempt to predict key milestones in AI development, on the path to AGI and super-human artificial intelligence. It’s still early days for this space, but it’s received attention from an increasing number of the AI safety and AI capabilities researchers. One of those researchers is Owain Evans, whose work at Oxford University’s Future of Humanity Institute is focused on techniques for learning about human beliefs, preferences and values from observing human behavior or interacting with humans. Owain joined me for this episode of the podcast to talk about AI forecasting, the problem of inferring human values, and the ecosystem of research organizations that support this type of research.
48 min
Machine Learning Street Talk
Machine Learning Street Talk
Machine Learning Street Talk
#037 - Tour De Bayesian with Connor Tann
Connor Tan is a physicist and senior data scientist working for a multinational energy company where he co-founded and leads a data science team. He holds a first-class degree in experimental and theoretical physics from Cambridge university. With a master's in particle astrophysics. He specializes in the application of machine learning models and Bayesian methods. Today we explore the history, pratical utility, and unique capabilities of Bayesian methods. We also discuss the computational difficulties inherent in Bayesian methods along with modern methods for approximate solutions such as Markov Chain Monte Carlo. Finally, we discuss how Bayesian optimization in the context of automl may one day put Data Scientists like Connor out of work. Panel: Dr. Keith Duggar, Alex Stenlake, Dr. Tim Scarfe 00:00:00 Duggars philisophical ramblings on Bayesianism 00:05:10 Introduction 00:07:30 small datasets and prior scientific knowledge 00:10:37 Bayesian methods are probability theory 00:14:00 Bayesian methods demand hard computations 00:15:46 uncertainty can matter more than estimators 00:19:29 updating or combining knowledge is a key feature 00:25:39 Frequency or Reasonable Expectation as the Primary Concept  00:30:02 Gambling and coin flips 00:37:32 Rev. Thomas Bayes's pool table 00:40:37 ignorance priors are beautiful yet hard 00:43:49 connections between common distributions 00:49:13 A curious Universe, Benford's Law 00:55:17 choosing priors, a tale of two factories 01:02:19 integration, the computational Achilles heel 01:35:25 Bayesian social context in the ML community 01:10:24 frequentist methods as a first approximation 01:13:13 driven to Bayesian methods by small sample size 01:18:46 Bayesian optimization with automl, a job killer? 01:25:28 different approaches to hyper-parameter optimization 01:30:18 advice for aspiring Bayesians 01:33:59 who would connor interview next? Connor Tann: https://www.linkedin.com/in/connor-tann-a92906a1/ https://twitter.com/connossor
1 hr 35 min
Learning Bayesian Statistics
Learning Bayesian Statistics
Alexandre ANDORRA
#31 Bayesian Cognitive Modeling & Decision-Making, with Michael Lee
I don’t know if you noticed, but I have a fondness for any topic related to decision-making under uncertainty — when it’s studied scientifically of course. Understanding how and why people make decisions when they don’t have all the facts is fascinating to me. That’s why I like electoral forecasting and I love cognitive sciences. So, for the first episode of 2021, I have a special treat: I had the great pleasure of hosting Michael Lee on the podcast! Yes, the Michael Lee who co-authored the book Bayesian Cognitive Modeling with Eric-Jan Wagenmakers in 2013 — by the way, the book was ported to PyMC3, I put the link in the show notes ;) This book was inspired from Michael’s work as a professor of cognitive sciences at University of California, Irvine. He works a lot on representation, memory, learning, and decision making, with a special focus on individual differences and collective cognition. Using naturally occurring behavioral data, he builds probabilistic generative models to try and answer hard real-world questions: how does memory impairment work (that’s modeled with multinomial processing trees)? How complex are simple decisions, and how do people change strategies? Echoing episode 18 with Daniel Lakens, Michael and I also talked about the reproducibility crisis: how are cognitive sciences doing, which progress was made, and what is still to do? Living now in California, Michael is originally from Australia, where he did his Bachelors of Psychology and Mathematics, and his PhD in psychology. But Michael is also found of the city of Amsterdam, which he sees as “the perfect antidote to southern California with old buildings, public transport, great bread and beer, and crappy weather”. Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ (https://bababrinkman.com/) ! Thank you to my Patrons for making this episode possible! Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Vincent Arel-Bundock, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll and Nathaniel Burbank. Visit https://www.patreon.com/learnbayesstats (https://www.patreon.com/learnbayesstats) to unlock exclusive Bayesian swag ;) Links from the show: Michael's website: https://faculty.sites.uci.edu/mdlee/ (https://faculty.sites.uci.edu/mdlee/) Michael on GitHub: https://twitter.com/mdlBayes (https://twitter.com/mdlBayes) Bayesian Cognitive Modeling book: https://faculty.sites.uci.edu/mdlee/bgm/ (https://faculty.sites.uci.edu/mdlee/bgm/) Bayesian Cognitive Modeling in PyMC3: https://github.com/pymc-devs/resources/tree/master/BCM (https://github.com/pymc-devs/resources/tree/master/BCM) An application of multinomial processing tree models and Bayesian methods to understanding memory impairment: https://drive.google.com/file/d/1NHml_YUsnpbUaqFhu0h8EiLeJCx6q403/view (https://drive.google.com/file/d/1NHml_YUsnpbUaqFhu0h8EiLeJCx6q403/view) Understanding the Complexity of Simple Decisions -- Modeling Multiple Behaviors and Switching Strategies: https://webfiles.uci.edu/mdlee/LeeGluckWalsh2018.pdf (https://webfiles.uci.edu/mdlee/LeeGluckWalsh2018.pdf) Robust Modeling in Cognitive Science: https://link.springer.com/article/10.1007/s42113-019-00029-y (https://link.springer.com/article/10.1007/s42113-019-00029-y) This podcast uses the following third-party services for analysis: Podcorn - https://podcorn.com/privacy Support this podcast
1 hr 9 min
More episodes
Search
Clear search
Close search
Google apps
Main menu