In July, AI scientists from around the globe gathered in virtual attendance for the 37th annual International Conference on Machine Learning (ICML).
Co-located with the conference was the AutoML@ICML2020 workshop, focused on different fields of ML connected to AutoML, such as neural architecture search, hyperparameter optimization, meta-learning, and learning to learn.
During that workshop, Alex Smola, AWS vice president and distinguished scientist, gave a virtual keynote to machine learning researchers and domain experts on automatic machine learning for tabular data.
Below is Smola’s keynote presentation, in which he provides an overview of AutoML techniques used in AutoGluon Tabular, an open-source library for developers building applications involving machine learning with image, text, or tabular data sets. With AutoGluon, developers can harness the power of deep learning for building applications by writing just a few lines of code.
AutoGluon Overview ICML’20 Workshop
Alex Smola, AWS vice president and distinguished scientist
