Today we’re joined by Alex Smola, Vice President and Distinguished Scientist at AWS AI.
Subscribe: iTunes / Google Play / Spotify / RSS
We had the pleasure to catch up with Alex prior to the upcoming AWS Machine Learning Summit, and we covered a TON of ground in the conversation. We start by focusing on his research in the domain of deep learning on graphs, including a few examples showcasing its function, and an interesting discussion around the relationship between large language models and graphs. Next up, we discuss their focus on AutoML research and how it’s the key to lowering the barrier of entry for machine learning research.
Alex also shares a bit about his work on causality and causal modeling, introducing us to the concept of Granger causality. Finally, we talk about the aforementioned ML Summit, it’s exponential growth since its inception a few years ago, and what speakers he’s most excited about hearing from.
Thanks to our Sponsor
Big thanks to our friends at Amazon Web Services for their continued support of the podcast, and their sponsorship of today’s show! If you’re not already, there is still time to register for the upcoming AWS Machine Learning Summit! On Wednesday, June 2nd beginning at 8 am PDT, some of the brightest minds in machine learning will come together to dive deep into the art, science, and impact of ML. You’ll hear from industry luminaries and leading experts on the latest breakthroughs, get real-world insights on how ML is impacting businesses, and learn best practices in building ML at your organization. The Machine Learning Summit is a free event, with more than 30 sessions featuring speakers including Andrew Ng and a variety of distinguished scientists and ML implementers, plus technical sessions and live Q&A with AWS Technical Community Leaders. Visit twimlai.com/awsmlsummit now to register and stay tuned to the pod for more interviews from the event!
Connect with Alex!
- AWS Machine Learning Summit – Session Details – Register Now!
- AutoGluon: AutoML for Text, Image, and Tabular Data
- Paper: AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
- Paper: Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation
- Deep Graph Library
- Amazon Neptune ML – Easy, fast, and accurate predictions for graphs
- Paper: Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
- Detecting and Correcting for Label Shift with Black Box Predictors
- Who Supported Obama in 2012? Ecological Inference through Distribution Regression
- Linear-Time Estimators for Propensity Scores
- Doubly Robust Covariate Shift Correction
- Dive into Deep Learning
- Paper: Feature relevance quantification in explainable AI: A causal problem