1,113 subscribers
Go offline with the Player FM app!
863: TabPFN: Deep Learning for Tabular Data (That Actually Works!), with Prof. Frank Hutter
Manage episode 467249047 series 1278026
Jon Krohn talks tabular data with Frank Hutter, Professor of Artificial Intelligence at Universität Freiburg in Germany. Despite the great steps that deep learning has made in analysing images, audio, and natural language, tabular data has remained its insurmountable obstacle. In this episode, Frank Hutter details the path he has found around this obstacle even with limited data by using a ground-breaking transformer architecture. Named TabPFN, this approach is vastly outperforming other architectures, as testified by a write up of TabPFN’s capabilities in Nature. Frank talks about his work on version 2 of TabPFN, the architecture’s cross-industry applicability, and how TabPFN is able to return accurate results with synthetic data.
This episode is brought to you by ODSC, the Open Data Science Conference. Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
- (05:57) All about the TabPFN architecture
- (21:27) Use cases for Bayesian inference
- (35:07) On getting published in Nature
- (44:03) How TabPFN handles time series data
- (51:52) All about Prior Labs
Additional materials: www.superdatascience.com/863
1192 episodes
Manage episode 467249047 series 1278026
Jon Krohn talks tabular data with Frank Hutter, Professor of Artificial Intelligence at Universität Freiburg in Germany. Despite the great steps that deep learning has made in analysing images, audio, and natural language, tabular data has remained its insurmountable obstacle. In this episode, Frank Hutter details the path he has found around this obstacle even with limited data by using a ground-breaking transformer architecture. Named TabPFN, this approach is vastly outperforming other architectures, as testified by a write up of TabPFN’s capabilities in Nature. Frank talks about his work on version 2 of TabPFN, the architecture’s cross-industry applicability, and how TabPFN is able to return accurate results with synthetic data.
This episode is brought to you by ODSC, the Open Data Science Conference. Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
- (05:57) All about the TabPFN architecture
- (21:27) Use cases for Bayesian inference
- (35:07) On getting published in Nature
- (44:03) How TabPFN handles time series data
- (51:52) All about Prior Labs
Additional materials: www.superdatascience.com/863
1192 episodes
All episodes
×

1 883: Blackwell GPUs Are Now Available at Your Desk, with Sama Bali and Logan Lawler 1:04:03


1 882: 40x Hotter Than the Sun: The ASML Machines That Make AI Chips 9:45


1 881: Beyond GPUs: The Power of Custom AI Accelerators, with Emily Webber 1:17:06




1 879: Serverless, Parallel, and AI-Assisted: The Future of Data Science is Here, with Zerve’s Dr. Greg Michaelson 1:07:14




1 877: The Neural Processing Units Bringing AI to PCs, with Shirish Gupta 1:09:32


1 876: Hugging Face’s smolagents: Agentic AI in Python Made Easy 15:11


1 875: How Semiconductors Are Made (And Fuel the AI Boom), with Kai Beckmann 1:10:29


1 874: How AI is Transforming Baseball (with Lessons For All of Us) 14:27


1 873: Become Your Best Self Through AI Augmentation — feat. Natalie Monbiot 1:12:32


1 872: Microsoft’s “Majorana 1” Chip Brings Quantum ML Closer 12:20


1 871: NoSQL Is Ideal for AI Applications, with MongoDB’s Richmond Alake 1:13:11


1 870: OpenAI’s “Deep Research”: Get Days of Human Work Done in Minutes 17:22


1 869: AI Should Make Humans Wiser (But It Isn’t), with Varun Godbole 1:19:42
Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.