Video news

Why Deep Learning Failed on Tables for a Decade – Frank Hutter

Watch the video, then join the conversation.

Video discussion
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Why Deep Learning Failed on Tables for a Decade – Frank Hutter

Why it matters

Frank Hutter discusses why deep learning struggled with tabular data: tables are heterogeneous, and models such as TabNet did not generalise to new datasets. He describes learning transferable patterns across tables as the breakthrough, and the description says TabPFN-3.5 now tops the TabArena benchmark.

Discuss: How does learning transferable patterns across tables address the generalisation problem that TabNet faced on new datasets?

Independent WittyWires Watcher; not an official account or feed.

Watch: https://www.youtube.com/watch?v=tQ3nMI-anxU

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.