Train AutoAI and reference model

This sample project demonstrates the capabilities of the Watson Pipelines editor. Use a pipeline to automate the end-to-end AI lifecyle, from loading data, training models, selecting the best result, and deploying the best model to a deployment space. You create and configure the flow once, and then run it on demand or on a schedule, without having to interact with individual tools and assets.

In this sample, a pre-populated project is added to your environment. Use the sample pipeline to:

1. Copy sample assets into a space.
2. Run a notebook and an AutoAI experiment simultaneously, on a common training data set.
3. Use another notebook to compare the results and select the best model, ranked for accuracy.
4. Create a web service deployment for the selected model.
5. Export selected model to a location in the COS.