The Past, Present and the Future of Machine Learning for Tabular Data - Bojan Tunguz

In this talk you will learn about the history and future directions of machine learning for Tabular Data. The talk a covers
• What is Tabular Data?
• The Main Issues with Tabular Data
• Deep Learning vs. Gradient Boosted Trees
• Research Directions
• GPU Acceleration
Bojan Tunguz, PhD is a Quadruple Kaggle Grandmaster and a Senior Software Systems Engineer at NVIDIA
✅ Connect with Bojan: / tunguz
✅ Connect with Southern Data Science Conference on LinkedIn - / southerndatasciencecon...
✅ Connect with Southern Data Science Conference on Twitter:
/ southerndsc

[@carvalhoribeiro]

Thanks for sharing this ! This presentation was very valuable. This 3rd generation view(past, present, future) raises a lot of questions in my mind.
• What business areas(industry, agriculture, constructions, small business) we could apply the machine learning techniques to improve productivity ?
• How to turn a vast amount of tabular data available into good resources(good raw material) for theses models?
• How to acquire better quality, standardized and comparable data (e.g. sensors, transfer learning from dl models etc) ?
Thank you all for sharing with us and congratulations Mr. Tunguz for this presentation.