Tracking accuracy to optimize model scaling

As we saw in Chapter 15, Automated Machine Learning and Transfer Learning, most machine learning algorithms employ a series of parameters that control the functionality of the underlying algorithm. These parameters are generally called hyperparameters; their values influence the quality of trained models. Automatic model optimization is the process of finding a set of hyperparameters of an algorithm that offer an optimal model. In this recipe, we will learn how to use the Amazon SageMaker tools to optimize our model automatically.

How to do it...

To perform an automatic optimization of our model, follow these steps:

1. Open the Amazon SageMaker console.
2. Select the Endpoint item in...