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


Speaker Bio

Mikael Huss – Founder & Data Scientist | Codon Consulting

Mikael is currently co-founder & principal data scientist at Codon Consulting, a company which builds machine learning systems for a variety of clients in life science, agriculture, finance and other sectors. After a research career in Singapore and Stockholm, which resulted in a PhD and an associate professor title in bioinformatics from KTH, he decided to pursue his long-standing interest in machine learning and in industry. This led him to work as a senior data scientist at IBM and Peltarion. After co-founding Codon, he has devoted his attention to things like transformer models in biology, content moderation with language models, and crop yield forecasting with computer vision. Mikael has also previously been an active participant in Stockholm’s meetup ecosystem as a meetup organizer and speaker for Stockholm AI and SRUG (Stockholm R useR group). He’s excited about large language models and the convergence of AI and biology.

November 9 @ 13:50
13:50 — 14:20 (30′)

Day 2 | 9 Nov 2022 | STRATEGY + ORGANISATION

Mikael Huss – Founder & Data Scientist | Codon Consulting