The Azure Machine Learning Studio activities are called experiments. An experiment consists of datasets that provide data to analytical modules, which are linked together to build a machine learning model.
The following are the essential steps of a project:
- Get the data
- Prepare the data
- Train the model
- Score and evaluate the model
- Use the model
To create a new experiment, just click on the + button at the bottom-left and a pop-up window will open, providing the following options:
- Blank experiment
- Experiment tutorial
- Some sample experiment
The following screenshot shows an overview of the pop-up window opened:
The essential elements of an experiment are:
- Dataset
- Module
Let's describe them in ...