From the course: Machine Learning with SageMaker by Pearson

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

Hyperparameter tuning with SageMaker automatic model tuning

Hyperparameter tuning with SageMaker automatic model tuning - Amazon SageMaker Tutorial

From the course: Machine Learning with SageMaker by Pearson

Start my 1-month free trial Buy for my team

Hyperparameter tuning with SageMaker automatic model tuning

“

I mentioned hyperparameter tuning in the previous lesson, but what is it? It is we are going to manipulate the configured hyperparameters on our model to try to optimize and make our model better. Things like learning rate, batch size can be manipulated in order to try to speed up the creation of our model, as well as improve accuracy. So automatic model tuning within SageMaker is a feature that allows you to attempt to improve a model's performance by doing the automation of hyperparameter optimization. It will also assist in distributing your training across multiple instances. It does support Bayesian optimization for smarter searches. This is where it's going to create a model Say, for example, create three different models and then choose the best one as far as manipulating a single hyperparameter. And then that particular one is chosen as input for the next attempt. SageMaker Automatic Model Tuning is going to basically manipulate hyperparameters across a range. It's considered…

Contents