863: TabPFN: Deep Learning for Tabular Data (That Actually Works!), with Prof. Frank Hutter
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Deep Learning for Tabular Data
This chapter explores deep learning techniques for tabular data, emphasizing the challenge of limited high-quality datasets. It introduces prior data-fitted networks (PFNs) and their role in generating synthetic data to enhance model training. Additionally, the discussion covers Bayesian inference, predictive distributions, and the advantages of integrating prior knowledge into machine learning models.
Transcript
Play full episode
