Hyperight

Deep learning on tabular data (the world’s most common type of data); is it worth it? – Mikael Huss, Codon Consulting

Premium content

Login or register to unlock the content

Session Outline

Deep learning has revolutionized fields like computer vision and NLP, but in the case of tabular data, methods like gradient boosting are still holding strong. The past few years have seen innovative amthods based on transformers for tabular data, such as TabNet, SAINT, Hopular, TabFPN. Let’s find out if these methods are gradient boosting killers or overhyped!

Key Takeaways

– What makes gradient boosting a strong competitor for DL on tabular data in particular

– Which are the concrete innovations brought by the transformer-based models?

– Practical considerations for selecting your tabular data classification/regression algorithm

Add comment

Highlight option

Turn on the "highlight" option for any widget, to get an alternative styling like this. You can change the colors for highlighted widgets in the theme options. See more examples below.

Instagram

Instagram has returned empty data. Please authorize your Instagram account in the plugin settings .

Ivana Kotorchevikj

Categories count color

Advertisement

Small ads

Flickr

  • Herr Krähenfüß
  • Sarah
  • Matty
  • on rear
  • Traffic lights
  • WoMo
  • Presentation
  • endless
  • stand still screening-smoking girl

Social Widget

Collaboratively harness market-driven processes whereas resource-leveling internal or "organic" sources.

ThemeForest