Before you start this exercise, ensure that you have completed the previous execise.
You've trained a model using a particular algorithm and hyperparameter settings, with moderate, but not great, results. With Azure ML you have the ability to leverage scalable cloud compute, so it's time to use it to scale out your training experiments and try multiple combinations of algorithms and parameters to find the optimal model.
- Start your Notebook VM and connect to Jupyter.
- In the /mlads-aml/notebooks folder, open the 02 - Optimizing Model Training.ipynb notebook.
- Read the notes in the notebook, running each code cell in turn.
Note: If you intend to continue straight to the next exercise, leave your Notebook VM running. If you're taking a break, you might want to close the Jupyter tabs and Stop your Notebook VM to avoid incurring unnecessary costs.