53 subscribers
با برنامه Player FM !
پادکست هایی که ارزش شنیدن دارند
حمایت شده


1 LIVE: Before the Chorus & Open Folk Present: In These Lines feat. Gaby Moreno, Lily Kershaw & James Spaite 33:58
863: TabPFN: Deep Learning for Tabular Data (That Actually Works!), with Prof. Frank Hutter
Manage episode 467254505 series 2532807
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
987 قسمت
Manage episode 467254505 series 2532807
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
987 قسمت
Kaikki jaksot
×
1 909: Causal AI, with Dr. Robert Usazuwa Ness 1:22:27


1 907: Neuroscience, AI and the Limitations of LLMs, with Dr. Zohar Bronfman 1:21:16


1 905: Why RAG Makes LLMs Less Safe (And How to Fix It), with Bloomberg’s Dr. Sebastian Gehrmann 57:49


1 903: LLM Benchmarks Are Lying to You (And What to Do Instead), with Sinan Ozdemir 1:28:20

1 901: Automating Legal Work with Data-Centric ML (feat. Lilith Bat-Leah) 1:06:12


1 899: Landing $200k+ AI Roles: Real Cases from the SuperDataScience Community, with Kirill Eremenko 1:33:12


1 897: How to Enable Enterprise AI Transformation, with Strategy Consultant Diane Hare 1:02:42


1 895: The Future of Enterprise AI: Investor Shaun Johnson Reveals What Actually Works 1:16:26

1 893: How to Jumpstart Your Data Career (by Applying Like a Scientist), with Avery Smith 1:17:51


1 891: Conversational AI is Overhauling Data Analytics, with Martin Brunthaler 1:02:08

1 889: AI-Powered Virtual Reality: The Future of Education and Entertainment, with Mary Spio 1:06:59


1 887: Multi-Agent Teams, Quantum Computing and the Future of Work, with Dell’s Global CTO John Roese 1:02:04

1 885: Python Polars: The Definitive Guide, with Jeroen Janssens and Thijs Nieuwdorp 1:15:22


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


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


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


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


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


1 869: AI Should Make Humans Wiser (But It Isn’t), with Varun Godbole 1:19:42


1 867: LLMs and Agents Are Overhyped, with Dr. Andriy Burkov 1:33:12




1 863: TabPFN: Deep Learning for Tabular Data (That Actually Works!), with Prof. Frank Hutter 1:06:06


1 861: From Pro Athlete to Data Engineer: Colleen Fotsch’s Inspiring Journey 2:00:42




1 857: How to Ensure AI Agents Are Accurate and Reliable, with Brooke Hopkins 1:22:43


1 855: Exponential Views on AI and Humanity’s Greatest Challenges, with Azeem Azhar 1:28:12


1 853: Generative AI for Business, with Kirill Eremenko and Hadelin de Ponteves 1:29:00


1 851: Quantum ML: Real-World Applications Today, with Dr. Florian Neukart 1:11:51


1 833: The 10 Reasons AI Projects Fail, with Dr. Martin Goodson 1:25:25

1 831: PyTorch Lightning, Lit-Serve and Lightning Studios, with Dr. Luca Antiga 1:23:23


1 829: Neuroscience Fueled by ML, with Prof. Bradley Voytek 1:36:58


1 827: Polars: Past, Present and Future, with Polars Creator Ritchie Vink 1:13:41


1 825: Data Contracts: The Key to Data Quality, with Chad Sanderson 1:02:22


1 823: Virtual Humans and AI Clones, with Natalie Monbiot 1:20:35


1 821: The Skills You Need to Be an Effective Data Scientist, with Marck Vaisman 1:13:14

1 819: PyTorch: From Zero to Hero, with Luka Anicin 1:06:05


1 817: The Positron IDE, Tidy NLP and MLOps with Dr. Julia Silge 1:36:11

1 815: Polars: Faster DataFrame Ops, with Marco Gorelli 1:27:18


1 813: Solving Business Problems Optimally with Data, with Jerry Yurchisin 1:43:30


1 811: Scaling Data Science Teams Effectively, with Nick Elprin 1:14:06

1 809: Agentic AI, with Shingai Manjengwa 1:10:19

1 807: Superintelligence and the Six Singularities, with Dr. Daniel Hulme 1:09:23


به Player FM خوش آمدید!
Player FM در سراسر وب را برای یافتن پادکست های با کیفیت اسکن می کند تا همین الان لذت ببرید. این بهترین برنامه ی پادکست است که در اندروید، آیفون و وب کار می کند. ثبت نام کنید تا اشتراک های شما در بین دستگاه های مختلف همگام سازی شود.