Machine Learning on Tabular Data with Nyckel

. In the video, the instructor used one of the most popular datasets on kaggle - the titanic dataset. It lists data on titanic passengers (name, age, number of siblings, ticket class, etc.) with a column that indicates whether the passenger survived the shipwreck. The challenge is to create a model that predicts which passengers survived. In less that two minutes, the system is able to go from the data to a trained and deployed model. Underneath this serene user experience, there is a lot going on: (1)Training-optimized cloud hardware is allocated, (2)Several state-of-the-art deep neural networks and hyper-parameters are evaluated to find the best fit for the data, (3)The model is deployed on inference-optimized and elastically scalable cloud hardware, behind a secure REST API . . https://www.nyckel.com/blog/fast-machine-learning-tabular-data-automl/